Amir Dezfouli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Amir Dezfouli has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Peter Dayan
Max Planck Institute for Biological Cybernetics, Tübingen, Germany
5 shared publications - Bernard Walter Balleine
Decision Neuroscience Laboratory, School of Psychology, UNSW Sydney
4 shared publications Richard Nock
DATA61, CSIRO
3 shared publications- Benjamin Ward Muir
CSIRO Manufacturing
2 shared publications - Fabio Ramos
NVIDIA, Santa Clara, CA, USA
2 shared publications - Iadine Chadès
The Environmental Informatics Hub, Department of Data Science and AI Monash University Melbourne Victoria Australia
2 shared publications
Latest Publications
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (9) , 11506-11514
Mixed-Variable Black-Box Optimisation Using Value Proposal Trees
Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such as Bayesian Optimisation (BO) are ill-equipped to handle such mixed-variable search spaces. The optimisation breadth introduced by categorical variables in the mixed-input setting has seen recent approaches operating on local trust regions, but these methods can be greedy in suboptimal regions of the search space. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We develop a tree-based method which retains a global view of the optimisation spaces by identifying regions in the search space with high potential candidates which we call value proposals. Our method uses these proposals to make selections on both the categorical and continuous components of the input. We show that this approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (9) , 11506-11514
Open AccessMixed-Variable Black-Box Optimisation Using Value Proposal Trees
Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such as Bayesian Optimisation (BO) are ill-equipped to handle such mixed-variable search spaces. The optimisation breadth introduced by categorical variables in the mixed-input setting has seen recent approaches operating on local trust regions, but these methods can be greedy in suboptimal regions of the search space. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We develop a tree-based method which retains a global view of the optimisation spaces by identifying regions in the search space with high potential candidates which we call value proposals. Our method uses these proposals to make selections on both the categorical and continuous components of the input. We show that this approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.
- Open Access
Bayesian Optimisation for Mixed-Variable Inputs using Value Proposals
Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such asBayesian Optimisation (BO) are not designed tohandle such mixed-variable search spaces. Recent approaches to this problem cast the selection of the categorical variables as a bandit problem, operating independently alongside a BO component which optimises the continuous variables. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We derive candidates from the ExpectedImprovement criterion, which we call value proposals, and use these proposals to make selections on both the categorical and continuous components of the input. We show that this unified approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.
Open AccessBayesian Optimisation for Mixed-Variable Inputs using Value Proposals
Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such asBayesian Optimisation (BO) are not designed tohandle such mixed-variable search spaces. Recent approaches to this problem cast the selection of the categorical variables as a bandit problem, operating independently alongside a BO component which optimises the continuous variables. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We derive candidates from the ExpectedImprovement criterion, which we call value proposals, and use these proposals to make selections on both the categorical and continuous components of the input. We show that this unified approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.
- Open Access
TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. The proposed framework is able to learn proof search strategies as well as tactic and arguments prediction in an end-to-end manner. We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart from promising alternatives. We implement the framework in the HOL4 theorem prover. Experimental results show that the framework outperforms existing automated theorem provers (i.e., hammers) available in HOL4 when evaluated on unseen problems. We further elaborate the role of key components of the framework using ablation studies.
Open AccessTacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. The proposed framework is able to learn proof search strategies as well as tactic and arguments prediction in an end-to-end manner. We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart from promising alternatives. We implement the framework in the HOL4 theorem prover. Experimental results show that the framework outperforms existing automated theorem provers (i.e., hammers) available in HOL4 when evaluated on unseen problems. We further elaborate the role of key components of the framework using ablation studies.
- 1 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 16 (1) , 591-602
EAPS: Edge-Assisted Predictive Sleep Scheduling for 802.11 IoT Stations
The broad deployment of 802.11 (a.k.a. Wi-Fi) access points and the significant energy-efficiency improvement of 802.11 transceivers have resulted in increasing interest in building 802.11-based Internet of Things (IoT) systems. Unfortunately, the power saving mechanisms of 802.11 fall short when used in IoT applications, especially because they do not take into account the delays caused by various factors, such as buffering, interference, and round-trip delay. In this article, we present edge-assisted predictive sleep scheduling (EAPS) to adjust the sleep duration of stations while they are expecting downlink packets. We first implement a Linux-based access point that enables us to collect parameters affecting communication latency. Using this access point, we build a testbed that, in addition to offering traffic pattern customization, replicates the characteristics of real-world environments. We then use multiple machine learning algorithms to predict downlink packet delivery. Our empirical evaluations confirm that with EAPS, the energy consumption of IoT stations is as low as power save mode, whereas the delay of packet delivery is close to the case where the station is always awake.
- 1 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 16 (1) , 591-602
EAPS: Edge-Assisted Predictive Sleep Scheduling for 802.11 IoT Stations
The broad deployment of 802.11 (a.k.a. Wi-Fi) access points and the significant energy-efficiency improvement of 802.11 transceivers have resulted in increasing interest in building 802.11-based Internet of Things (IoT) systems. Unfortunately, the power saving mechanisms of 802.11 fall short when used in IoT applications, especially because they do not take into account the delays caused by various factors, such as buffering, interference, and round-trip delay. In this article, we present edge-assisted predictive sleep scheduling (EAPS) to adjust the sleep duration of stations while they are expecting downlink packets. We first implement a Linux-based access point that enables us to collect parameters affecting communication latency. Using this access point, we build a testbed that, in addition to offering traffic pattern customization, replicates the characteristics of real-world environments. We then use multiple machine learning algorithms to predict downlink packet delivery. Our empirical evaluations confirm that with EAPS, the energy consumption of IoT stations is as low as power save mode, whereas the delay of packet delivery is close to the case where the station is always awake.
- Open Access
- 4 November 2020
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 117 (46) , 29221-29228
Adversarial vulnerabilities of human decision-making
Significance: “What I cannot efficiently break, I cannot understand.” Understanding the vulnerabilities of human choice processes allows us to detect and potentially avoid adversarial attacks. We develop a general framework for creating adversaries for human decision-making. The framework is based on recent developments in deep reinforcement learning models and recurrent neural networks and can in principle be applied to any decision-making task and adversarial objective. We show the performance of the framework in three tasks involving choice, response inhibition, and social decision-making. In all of the cases the framework was successful in its adversarial attack. Furthermore, we show various ways to interpret the models to provide insights into the exploitability of human choice.
- 4 November 2020
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 117 (46) , 29221-29228
Open AccessAdversarial vulnerabilities of human decision-making
Significance: “What I cannot efficiently break, I cannot understand.” Understanding the vulnerabilities of human choice processes allows us to detect and potentially avoid adversarial attacks. We develop a general framework for creating adversaries for human decision-making. The framework is based on recent developments in deep reinforcement learning models and recurrent neural networks and can in principle be applied to any decision-making task and adversarial objective. We show the performance of the framework in three tasks involving choice, response inhibition, and social decision-making. In all of the cases the framework was successful in its adversarial attack. Furthermore, we show various ways to interpret the models to provide insights into the exploitability of human choice.
- Open Access
Neural Network Poisson Models for Behavioural and Neural Spike Train Data
A bstract: One of the most important and challenging application areas for complex machine learning methods is to predict, characterize and model rich, multi-dimensional, neural data. Recent advances in neural recording techniques have made it possible to monitor the activities of a large number of neurons across different brain regions as animals perform behavioural tasks. This poses the critical challenge of establishing links between neural activity at a microscopic scale, which might for instance represent sensory input, and at a macroscopic scale, which then generates behaviour. Predominant modeling methods apply rather disjoint techniques to these scales; by contrast, we suggest an end-to-end model which exploits recent developments of flexible, but tractable, neural network point-process models to characterize dependencies between stimuli, actions, and neural data. We apply this model to a public dataset collected using Neuropixel probes in mice performing a visually-guided behavioural task as well as a synthetic dataset produced from a hierarchical network model with reciprocally connected sensory and integration circuits intended to characterize animal behaviour in a fixed-duration motion discrimination task. We show that our model outperforms previous approaches and contributes novel insights into the relationships between neural activities and behaviour.
Open AccessNeural Network Poisson Models for Behavioural and Neural Spike Train Data
A bstract: One of the most important and challenging application areas for complex machine learning methods is to predict, characterize and model rich, multi-dimensional, neural data. Recent advances in neural recording techniques have made it possible to monitor the activities of a large number of neurons across different brain regions as animals perform behavioural tasks. This poses the critical challenge of establishing links between neural activity at a microscopic scale, which might for instance represent sensory input, and at a macroscopic scale, which then generates behaviour. Predominant modeling methods apply rather disjoint techniques to these scales; by contrast, we suggest an end-to-end model which exploits recent developments of flexible, but tractable, neural network point-process models to characterize dependencies between stimuli, actions, and neural data. We apply this model to a public dataset collected using Neuropixel probes in mice performing a visually-guided behavioural task as well as a synthetic dataset produced from a hierarchical network model with reciprocally connected sensory and integration circuits intended to characterize animal behaviour in a fixed-duration motion discrimination task. We show that our model outperforms previous approaches and contributes novel insights into the relationships between neural activities and behaviour.
- Open Access
Adversarial manipulation of human decision-making
Adversarial examples are carefully crafted input patterns that are surprisingly poorly classified by artificial and/or natural neural networks. Here we examine adversarial vulnerabilities in the processes responsible for learning and choice in humans. Building upon recent recurrent neural network models of choice processes, we propose a general framework for generating adversarial opponents that can shape the choices of individuals in particular decision-making tasks towards the behavioural patterns desired by the adversary. We show the efficacy of the framework through two experiments involving action selection and response inhibition. We further investigate the strategy used by the adversary in order to gain insights into the vulnerabilities of human choice. The framework may find applications across behavioural sciences in helping detect and avoid flawed choice.
Open AccessAdversarial manipulation of human decision-making
Adversarial examples are carefully crafted input patterns that are surprisingly poorly classified by artificial and/or natural neural networks. Here we examine adversarial vulnerabilities in the processes responsible for learning and choice in humans. Building upon recent recurrent neural network models of choice processes, we propose a general framework for generating adversarial opponents that can shape the choices of individuals in particular decision-making tasks towards the behavioural patterns desired by the adversary. We show the efficacy of the framework through two experiments involving action selection and response inhibition. We further investigate the strategy used by the adversary in order to gain insights into the vulnerabilities of human choice. The framework may find applications across behavioural sciences in helping detect and avoid flawed choice.
- Open Access
- 11 June 2019
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 15 (6) , e1006903
Models that learn how humans learn: The case of decision-making and its disorders
Popular computational models of decision-making make specific assumptions about learning processes that may cause them to underfit observed behaviours. Here we suggest an alternative method using recurrent neural networks (RNNs) to generate a flexible family of models that have sufficient capacity to represent the complex learning and decision- making strategies used by humans. In this approach, an RNN is trained to predict the next action that a subject will take in a decision-making task and, in this way, learns to imitate the processes underlying subjects’ choices and their learning abilities. We demonstrate the benefits of this approach using a new dataset drawn from patients with either unipolar (n = 34) or bipolar (n = 33) depression and matched healthy controls (n = 34) making decisions on a two-armed bandit task. The results indicate that this new approach is better than baseline reinforcement-learning methods in terms of overall performance and its capacity to predict subjects’ choices. We show that the model can be interpreted using off-policy simulations and thereby provides a novel clustering of subjects’ learning processes—something that often eludes traditional approaches to modelling and behavioural analysis. Computational models of decision-making provide a quantitative characterisation of the learning and choice processes behind human actions. Designing a computational model is often based on manual engineering which an iterative process to examine the consistency between different aspects of the model and the empirical data. In practice, however, inconsistencies between the model and observed behaviours can remain hidden behind examined summary statistics. To address this limitation, we developed a recurrent neural network (RNNs) as a flexible type of model that can automatically characterize human decision-making processes without requiring tweaking and engineering. To show the benefits of this new approach, we collected data on a decision-making task conducted on subjects with either bipolar or unipolar depression, as well as healthy controls. The results showed that, indeed, important aspects of decision-making remained uncaptured by typical computational models and even their enhanced variants, but were captured by RNNs automatically. Further, we were able to show that the nature of such processes can be unveiled by simulating the model under various conditions. This new approach can be used, therefore, as a standalone model of decision-making or as a baseline model to evaluate how well other candidate models fit observed data.
- 11 June 2019
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 15 (6) , e1006903
Open AccessModels that learn how humans learn: The case of decision-making and its disorders
Popular computational models of decision-making make specific assumptions about learning processes that may cause them to underfit observed behaviours. Here we suggest an alternative method using recurrent neural networks (RNNs) to generate a flexible family of models that have sufficient capacity to represent the complex learning and decision- making strategies used by humans. In this approach, an RNN is trained to predict the next action that a subject will take in a decision-making task and, in this way, learns to imitate the processes underlying subjects’ choices and their learning abilities. We demonstrate the benefits of this approach using a new dataset drawn from patients with either unipolar (n = 34) or bipolar (n = 33) depression and matched healthy controls (n = 34) making decisions on a two-armed bandit task. The results indicate that this new approach is better than baseline reinforcement-learning methods in terms of overall performance and its capacity to predict subjects’ choices. We show that the model can be interpreted using off-policy simulations and thereby provides a novel clustering of subjects’ learning processes—something that often eludes traditional approaches to modelling and behavioural analysis. Computational models of decision-making provide a quantitative characterisation of the learning and choice processes behind human actions. Designing a computational model is often based on manual engineering which an iterative process to examine the consistency between different aspects of the model and the empirical data. In practice, however, inconsistencies between the model and observed behaviours can remain hidden behind examined summary statistics. To address this limitation, we developed a recurrent neural network (RNNs) as a flexible type of model that can automatically characterize human decision-making processes without requiring tweaking and engineering. To show the benefits of this new approach, we collected data on a decision-making task conducted on subjects with either bipolar or unipolar depression, as well as healthy controls. The results showed that, indeed, important aspects of decision-making remained uncaptured by typical computational models and even their enhanced variants, but were captured by RNNs automatically. Further, we were able to show that the nature of such processes can be unveiled by simulating the model under various conditions. This new approach can be used, therefore, as a standalone model of decision-making or as a baseline model to evaluate how well other candidate models fit observed data.
- Open Access
Disentangled behavioral representations
Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects’ behavior and then studying differences between them in the associated parameter space. However, these models often fit behavior more poorly than recurrent neural networks (RNNs), which are more flexible and make fewer assumptions about the underlying decision-making processes. Unfortunately, the parameter and latent activity spaces of RNNs are generally high-dimensional and uninterpretable, making it hard to use them to study individual differences. Here, we show how to benefit from the flexibility of RNNs while representing individual differences in a low-dimensional and interpretable space. To achieve this, we propose a novel end-to-end learning framework in which an encoder is trained to map the behavior of subjects into a low-dimensional latent space. These low-dimensional representations are used to generate the parameters of individual RNNs corresponding to the decision-making process of each subject. We introduce terms into the loss function that ensure that the latent dimensions are informative and disentangled, i.e., encouraged to have distinct effects on behavior. This allows them to align with separate facets of individual differences. We illustrate the performance of our framework on synthetic data as well as a dataset including the behavior of patients with psychiatric disorders.
Open AccessDisentangled behavioral representations
Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects’ behavior and then studying differences between them in the associated parameter space. However, these models often fit behavior more poorly than recurrent neural networks (RNNs), which are more flexible and make fewer assumptions about the underlying decision-making processes. Unfortunately, the parameter and latent activity spaces of RNNs are generally high-dimensional and uninterpretable, making it hard to use them to study individual differences. Here, we show how to benefit from the flexibility of RNNs while representing individual differences in a low-dimensional and interpretable space. To achieve this, we propose a novel end-to-end learning framework in which an encoder is trained to map the behavior of subjects into a low-dimensional latent space. These low-dimensional representations are used to generate the parameters of individual RNNs corresponding to the decision-making process of each subject. We introduce terms into the loss function that ensure that the latent dimensions are informative and disentangled, i.e., encouraged to have distinct effects on behavior. This allows them to align with separate facets of individual differences. We illustrate the performance of our framework on synthetic data as well as a dataset including the behavior of patients with psychiatric disorders.
- Open Access
- 12 March 2019
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 15 (3) , e1006827
Optimizing the depth and the direction of prospective planning using information values
Evaluating the future consequences of actions is achievable by simulating a mental search tree into the future. Expanding deep trees, however, is computationally taxing. Therefore, machines and humans use a plan-until-habit scheme that simulates the environment up to a limited depth and then exploits habitual values as proxies for consequences that may arise in the future. Two outstanding questions in this scheme are “in which directions the search tree should be expanded?”, and “when should the expansion stop?”. Here we propose a principled solution to these questions based on a speed/accuracy tradeoff: deeper expansion in the appropriate directions leads to more accurate planning, but at the cost of slower decision-making. Our simulation results show how this algorithm expands the search tree effectively and efficiently in a grid-world environment. We further show that our algorithm can explain several behavioral patterns in animals and humans, namely the effect of time-pressure on the depth of planning, the effect of reward magnitudes on the direction of planning, and the gradual shift from goal-directed to habitual behavior over the course of training. The algorithm also provides several predictions testable in animal/human experiments. When faced with several choices in complex environments like chess, thinking about all the potential consequences of each choice, infinitely deep into the future, is simply impossible due to time and cognitive limitations. An outstanding question is what is the best direction and depth of thinking about the future? Here we propose a mathematical algorithm that computes, along the course of planning, the benefit of thinking another step in a given direction into the future, and compares that with the cost of thinking in order to compute the net benefit. We show that this algorithm is consistent with several behavioral patterns observed in humans and animals, suggesting that they, too, make efficient use of their time and cognitive resources when deciding how deep to think.
- 12 March 2019
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 15 (3) , e1006827
Open AccessOptimizing the depth and the direction of prospective planning using information values
Evaluating the future consequences of actions is achievable by simulating a mental search tree into the future. Expanding deep trees, however, is computationally taxing. Therefore, machines and humans use a plan-until-habit scheme that simulates the environment up to a limited depth and then exploits habitual values as proxies for consequences that may arise in the future. Two outstanding questions in this scheme are “in which directions the search tree should be expanded?”, and “when should the expansion stop?”. Here we propose a principled solution to these questions based on a speed/accuracy tradeoff: deeper expansion in the appropriate directions leads to more accurate planning, but at the cost of slower decision-making. Our simulation results show how this algorithm expands the search tree effectively and efficiently in a grid-world environment. We further show that our algorithm can explain several behavioral patterns in animals and humans, namely the effect of time-pressure on the depth of planning, the effect of reward magnitudes on the direction of planning, and the gradual shift from goal-directed to habitual behavior over the course of training. The algorithm also provides several predictions testable in animal/human experiments. When faced with several choices in complex environments like chess, thinking about all the potential consequences of each choice, infinitely deep into the future, is simply impossible due to time and cognitive limitations. An outstanding question is what is the best direction and depth of thinking about the future? Here we propose a mathematical algorithm that computes, along the course of planning, the benefit of thinking another step in a given direction into the future, and compares that with the cost of thinking in order to compute the net benefit. We show that this algorithm is consistent with several behavioral patterns observed in humans and animals, suggesting that they, too, make efficient use of their time and cognitive resources when deciding how deep to think.