Yali Amit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yali Amit has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Zhisheng Xiao
Computational and Applied Mathematics The University of Chicago
4 shared publications - Qing Yan
Department of Statistics University of Chicago 60637 Chicago IL
3 shared publications - Jiajun Shen
Department of Computer Science, University of Chicago, Chicago, Illinois 60637
2 shared publications A. Trouvé
USAEcole Normale Supérieur , Cachan, and Université Paris XIII , France
1 shared publicationAlain Trouvé
CMLA at the Ecole Normale Superieur, Cachan
1 shared publicationD. Geman
1 shared publication
Latest Publications
- Open Access
- 21 March 2022
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 16, 789253
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biologically plausible training we mean (i) all updates of weights are based oncurrentactivities of pre-synaptic units and current, or activity retrieved from short term memory of post synaptic units, including at the top-most error computing layer, (ii) complex computations such as normalization, inner products and division are avoided, (iii) asymmetric connections between units, and (iv) most learning is carried out in an unsupervised manner. SSL with a contrastive loss satisfies the third condition as it does not require labeled data and it introduces robustness to observed perturbations of objects, which occur naturally as objects or observers move in 3D and with variable lighting over time. We propose a contrastive hinge based loss whose error involves simple local computations satisfying (ii), as opposed to the standard contrastive losses employed in the literature, which do not lend themselves easily to implementation in a network architecture due to complex computations involving ratios and inner products. Furthermore, we show that learning can be performed with one of two more plausible alternatives to backpropagation that satisfy conditions (i) and (ii). The first is difference target propagation (DTP), which trains network parameters using target-based local losses and employs a Hebbian learning rule, thus overcoming the biologically implausible symmetric weight problem in backpropagation. The second is layer-wise learning, where each layer is directly connected to a layer computing the loss error. The layers are either updated sequentially in a greedy fashion (GLL) or in random order (RLL), and each training stage involves a single hidden layer network. Backpropagation through one layer needed for each such network can either be altered with fixed random feedback weights (RF) or using updated random feedback weights (URF) as in Amity's study 2019. Both methods represent alternatives to the symmetric weight issue of backpropagation. By training convolutional neural networks (CNNs) with SSL and DTP, GLL or RLL, we find that our proposed framework achieves comparable performance to standard BP learning downstream linear classifier evaluation of the learned embeddings.
- 21 March 2022
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 16, 789253
Open AccessBiologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biologically plausible training we mean (i) all updates of weights are based oncurrentactivities of pre-synaptic units and current, or activity retrieved from short term memory of post synaptic units, including at the top-most error computing layer, (ii) complex computations such as normalization, inner products and division are avoided, (iii) asymmetric connections between units, and (iv) most learning is carried out in an unsupervised manner. SSL with a contrastive loss satisfies the third condition as it does not require labeled data and it introduces robustness to observed perturbations of objects, which occur naturally as objects or observers move in 3D and with variable lighting over time. We propose a contrastive hinge based loss whose error involves simple local computations satisfying (ii), as opposed to the standard contrastive losses employed in the literature, which do not lend themselves easily to implementation in a network architecture due to complex computations involving ratios and inner products. Furthermore, we show that learning can be performed with one of two more plausible alternatives to backpropagation that satisfy conditions (i) and (ii). The first is difference target propagation (DTP), which trains network parameters using target-based local losses and employs a Hebbian learning rule, thus overcoming the biologically implausible symmetric weight problem in backpropagation. The second is layer-wise learning, where each layer is directly connected to a layer computing the loss error. The layers are either updated sequentially in a greedy fashion (GLL) or in random order (RLL), and each training stage involves a single hidden layer network. Backpropagation through one layer needed for each such network can either be altered with fixed random feedback weights (RF) or using updated random feedback weights (URF) as in Amity's study 2019. Both methods represent alternatives to the symmetric weight issue of backpropagation. By training convolutional neural networks (CNNs) with SSL and DTP, GLL or RLL, we find that our proposed framework achieves comparable performance to standard BP learning downstream linear classifier evaluation of the learned embeddings.
- Open Access
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biological plausible training we mean (i) All updates of weights are based on current activities of pre-synaptic units and current, or activity retrieved from short term memory of post synaptic units, including at the top-most error computing layer, (ii) Complex computations such as normalization, inner products and division are avoided (iii) Asymmetric connections between units, (iv) Most learning is carried out in an unsupervised manner. SSL with a contrastive loss satisfies the third condition as it does not require labelled data and it introduces robustness to observed perturbations of objects, which occur naturally as objects or observer move in 3d and with variable lighting over time. We propose a contrastive hinge based loss whose error involves simple local computations satisfying (ii), as opposed to the standard contrastive losses employed in the literature, which do not lend themselves easily to implementation in a network architecture due to complex computations involving ratios and inner products. Furthermore we show that learning can be performed with one of two more plausible alternatives to backpropagation that satisfy conditions (i) and (ii). The first is difference target propagation (DTP) and the second is layer-wise learning (LL), where each layer is directly connected to a layer computing the loss error. Both methods represent alternatives to the symmetric weight issue of backpropagation. By training convolutional neural networks (CNNs) with SSL and DTP, LL, we find that our proposed framework achieves comparable performance to standard BP learning downstream linear classifier evaluation of the learned embeddings.
Open AccessBiologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biological plausible training we mean (i) All updates of weights are based on current activities of pre-synaptic units and current, or activity retrieved from short term memory of post synaptic units, including at the top-most error computing layer, (ii) Complex computations such as normalization, inner products and division are avoided (iii) Asymmetric connections between units, (iv) Most learning is carried out in an unsupervised manner. SSL with a contrastive loss satisfies the third condition as it does not require labelled data and it introduces robustness to observed perturbations of objects, which occur naturally as objects or observer move in 3d and with variable lighting over time. We propose a contrastive hinge based loss whose error involves simple local computations satisfying (ii), as opposed to the standard contrastive losses employed in the literature, which do not lend themselves easily to implementation in a network architecture due to complex computations involving ratios and inner products. Furthermore we show that learning can be performed with one of two more plausible alternatives to backpropagation that satisfy conditions (i) and (ii). The first is difference target propagation (DTP) and the second is layer-wise learning (LL), where each layer is directly connected to a layer computing the loss error. Both methods represent alternatives to the symmetric weight issue of backpropagation. By training convolutional neural networks (CNNs) with SSL and DTP, LL, we find that our proposed framework achieves comparable performance to standard BP learning downstream linear classifier evaluation of the learned embeddings.
- Open Access
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC algorithms such as Langevin dynamics. However, since MCMC in high-dimensional space converges extremely slowly, the current understanding of maximum likelihood training, which assumes approximate samples from the model can be drawn, is problematic. In this paper, we try to understand this training procedure by replacing Langevin dynamics with deterministic solutions of the associated gradient descent ODE. Doing so allows us to study the density induced by the dynamics (if the dynamics are invertible), and connect with GANs by treating the dynamics as generator models, the initial values as latent variables and the loss as optimizing a critic defined by the very same energy that determines the generator through its gradient. Hence the term - self-adversarial loss. We show that reintroducing the noise in the dynamics does not lead to a qualitative change in the behavior, and merely reduces the quality of the generator. We thus show that EBM training is effectively a self-adversarial procedure rather than maximum likelihood estimation.
Open AccessEBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC algorithms such as Langevin dynamics. However, since MCMC in high-dimensional space converges extremely slowly, the current understanding of maximum likelihood training, which assumes approximate samples from the model can be drawn, is problematic. In this paper, we try to understand this training procedure by replacing Langevin dynamics with deterministic solutions of the associated gradient descent ODE. Doing so allows us to study the density induced by the dynamics (if the dynamics are invertible), and connect with GANs by treating the dynamics as generator models, the initial values as latent variables and the loss as optimizing a critic defined by the very same energy that determines the generator through its gradient. Hence the term - self-adversarial loss. We show that reintroducing the noise in the dynamics does not lead to a qualitative change in the behavior, and merely reduces the quality of the generator. We thus show that EBM training is effectively a self-adversarial procedure rather than maximum likelihood estimation.
- Open Access
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, some recent studies show that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that many of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances when applied to VAEs.
Open AccessLikelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, some recent studies show that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that many of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances when applied to VAEs.
- Open Access
A Method to Model Conditional Distributions with Normalizing Flows
In this work, we investigate the use of normalizing flows to model conditional distributions. In particular, we use our proposed method to analyze inverse problems with invertible neural networks by maximizing the posterior likelihood. Our method uses only a single loss and is easy to train. This is an improvement on the previous method that solves similar inverse problems with invertible neural networks but which involves a combination of several loss terms with ad-hoc weighting. In addition, our method provides a natural framework to incorporate conditioning in normalizing flows, and therefore, we can train an invertible network to perform conditional generation. We analyze our method and perform a careful comparison with previous approaches. Simple experiments show the effectiveness of our method, and more comprehensive experimental evaluations are undergoing.
Open AccessA Method to Model Conditional Distributions with Normalizing Flows
In this work, we investigate the use of normalizing flows to model conditional distributions. In particular, we use our proposed method to analyze inverse problems with invertible neural networks by maximizing the posterior likelihood. Our method uses only a single loss and is easy to train. This is an improvement on the previous method that solves similar inverse problems with invertible neural networks but which involves a combination of several loss terms with ad-hoc weighting. In addition, our method provides a natural framework to incorporate conditioning in normalizing flows, and therefore, we can train an invertible network to perform conditional generation. We analyze our method and perform a careful comparison with previous approaches. Simple experiments show the effectiveness of our method, and more comprehensive experimental evaluations are undergoing.
- Open Access
Generative Latent Flow
In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the distribution of the latent variables to that of simple i.i.d noise. In contrast to some other Auto-encoder based generative models, which use various regularizers that encourage the encoded latent distribution to match the prior distribution, our model explicitly constructs a mapping between these two distributions, leading to better density matching while avoiding over regularizing the latent variables. We compare our model with several related techniques, and show that it has many relative advantages including fast convergence, single stage training and minimal reconstruction trade-off. We also study the relationship between our model and its stochastic counterpart, and show that our model can be viewed as a vanishing noise limit of VAEs with flow prior. Quantitatively, under standardized evaluations, our method achieves state-of-the-art sample quality among AE based models on commonly used datasets, and is competitive with GANs' benchmarks.
Open AccessGenerative Latent Flow
In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the distribution of the latent variables to that of simple i.i.d noise. In contrast to some other Auto-encoder based generative models, which use various regularizers that encourage the encoded latent distribution to match the prior distribution, our model explicitly constructs a mapping between these two distributions, leading to better density matching while avoiding over regularizing the latent variables. We compare our model with several related techniques, and show that it has many relative advantages including fast convergence, single stage training and minimal reconstruction trade-off. We also study the relationship between our model and its stochastic counterpart, and show that our model can be viewed as a vanishing noise limit of VAEs with flow prior. Quantitatively, under standardized evaluations, our method achieves state-of-the-art sample quality among AE based models on commonly used datasets, and is competitive with GANs' benchmarks.
- 18 January 2019
- Published by American Mathematical Society (AMS) in Quarterly of Applied Mathematics
- Vol. 77 (2) , 207-226
Deformable classifiers
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
- 18 January 2019
- Published by American Mathematical Society (AMS) in Quarterly of Applied Mathematics
- Vol. 77 (2) , 207-226
Deformable classifiers
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
- Open Access
Deformable Classifiers
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
Open AccessDeformable Classifiers
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
- 27 October 2010
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 30 (3) , 699-720
Capacity analysis in multi-state synaptic models: a retrieval probability perspective
- 27 October 2010
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 30 (3) , 699-720
Capacity analysis in multi-state synaptic models: a retrieval probability perspective
- 23 January 2007
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 75 (2) , 267-282
POP: Patchwork of Parts Models for Object Recognition
- 23 January 2007
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 75 (2) , 267-282
POP: Patchwork of Parts Models for Object Recognition