Yash Sharma
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
Yash Sharma has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Mario Szegedy
Rutgers University
2 shared publications - Matthias Bethge
Tübingen AI Center, University of Tübingen
2 shared publications - Roland S. Zimmermann
Max Planck Institute for Dynamics and Self-Organization, Am Faßberg 17, 37077 Göttingen, Germany
2 shared publications - Ronald de Wolf
QuSoft CWI University of Amsterdam the Netherlands
2 shared publications - Sergey Bravyi
IBM T.J. Watson Research Center
2 shared publications Wieland Brendel
2 shared publications
Latest Publications
- Open Access
Averaging in gene perturbation benchmarks hides perturbation-strength variation: Consequences for model evaluation
Perturbation-response benchmarks usually represent each genetic intervention by averaging all cells assigned that perturbation label. We inquire what perturbation-strength information is lost by this averaging, and whether current model predictions preserve enough perturbation-specific information for this perturbation-strength variation to be evaluated. Using X-Atlas/Orion CRISPRi screens, we use depth-corrected guide abundance as a cell-level proxy for perturbation strength and examine how transcriptional responses vary within a nominal perturbation. Higher perturbation strength is associated with greater response reproducibility. The effect is present in two human cell lines, HCT116 and HEK293T, but is larger in HCT116. For model evaluation, HCT116 retrieval tests show that observed responses preserve perturbation identity, whereas the evaluated STATE and Cell2Sentence predictions do not reliably recover it, hence the question of within-perturbation strength information cannot be meaningfully evaluated.
Open AccessAveraging in gene perturbation benchmarks hides perturbation-strength variation: Consequences for model evaluation
Perturbation-response benchmarks usually represent each genetic intervention by averaging all cells assigned that perturbation label. We inquire what perturbation-strength information is lost by this averaging, and whether current model predictions preserve enough perturbation-specific information for this perturbation-strength variation to be evaluated. Using X-Atlas/Orion CRISPRi screens, we use depth-corrected guide abundance as a cell-level proxy for perturbation strength and examine how transcriptional responses vary within a nominal perturbation. Higher perturbation strength is associated with greater response reproducibility. The effect is present in two human cell lines, HCT116 and HEK293T, but is larger in HCT116. For model evaluation, HCT116 retrieval tests show that observed responses preserve perturbation identity, whereas the evaluated STATE and Cell2Sentence predictions do not reliably recover it, hence the question of within-perturbation strength information cannot be meaningfully evaluated.
- Open Access
- 14 May 2024
- Published by Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften in Quantum
- Vol. 8, 1348
Generating k EPR-pairs from an n -party resource state
Motivated by quantum network applications over classical channels, we initiate the study of n -party resource states from which LOCC protocols can create EPR-pairs between any k disjoint pairs of parties. We give constructions of such states where k is not too far from the optimal n / 2 while the individual parties need to hold only a constant number of qubits. In the special case when each party holds only one qubit, we describe a family of n -qubit states with k proportional to log n based on Reed-Muller codes, as well as small numerically found examples for k = 2 and k = 3 . We also prove some lower bounds, for example showing that if k = n / 2 then the parties must have at least Ω ( log log n ) qubits each.
- 14 May 2024
- Published by Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften in Quantum
- Vol. 8, 1348
Open AccessGenerating k EPR-pairs from an n -party resource state
Motivated by quantum network applications over classical channels, we initiate the study of n -party resource states from which LOCC protocols can create EPR-pairs between any k disjoint pairs of parties. We give constructions of such states where k is not too far from the optimal n / 2 while the individual parties need to hold only a constant number of qubits. In the special case when each party holds only one qubit, we describe a family of n -qubit states with k proportional to log n based on Reed-Muller codes, as well as small numerically found examples for k = 2 and k = 3 . We also prove some lower bounds, for example showing that if k = n / 2 then the parties must have at least Ω ( log log n ) qubits each.
- Open AccessGenerating $k$ EPR-pairs from an $n$-party resource stateMotivated by quantum network applications over classical channels, we initiate the study of $n$-party resource states from which LOCC protocols can create EPR-pairs between any $k$ disjoint pairs of parties. We give constructions of such states where $k$ is not too far from the optimal $n/2$ while the individual parties need to hold only a constant number of qubits. In the special case when each party holds only one qubit, we describe a family of $n$-qubit states with $k$ proportional to $\log n$ based on Reed-Muller codes, as well as small numerically found examples for $k=2$ and $k=3$. We also prove some lower bounds, for example showing that if $k=n/2$ then the parties must have at least $\Omega(\log\log n)$ qubits each.Open AccessGenerating $k$ EPR-pairs from an $n$-party resource stateMotivated by quantum network applications over classical channels, we initiate the study of $n$-party resource states from which LOCC protocols can create EPR-pairs between any $k$ disjoint pairs of parties. We give constructions of such states where $k$ is not too far from the optimal $n/2$ while the individual parties need to hold only a constant number of qubits. In the special case when each party holds only one qubit, we describe a family of $n$-qubit states with $k$ proportional to $\log n$ based on Reed-Muller codes, as well as small numerically found examples for $k=2$ and $k=3$. We also prove some lower bounds, for example showing that if $k=n/2$ then the parties must have at least $\Omega(\log\log n)$ qubits each.
- Open Access
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
As large-scale training regimes have gained popularity, the use of pretrained models for downstream tasks has become common practice in machine learning. While pretraining has been shown to enhance the performance of models in practice, the transfer of robustness properties from pretraining to downstream tasks remains poorly understood. In this study, we demonstrate that the robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation, regardless of the protocol used for pretraining. We prove (i) a bound on the loss that holds independent of any downstream task, as well as (ii) a criterion for robust classification in particular. We validate our theoretical results in practical applications, show how our results can be used for calibrating expectations of downstream robustness, and when our results are useful for optimal transfer learning. Taken together, our results offer an initial step towards characterizing the requirements of the representation function for reliable post-adaptation performance.
Open AccessOn Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
As large-scale training regimes have gained popularity, the use of pretrained models for downstream tasks has become common practice in machine learning. While pretraining has been shown to enhance the performance of models in practice, the transfer of robustness properties from pretraining to downstream tasks remains poorly understood. In this study, we demonstrate that the robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation, regardless of the protocol used for pretraining. We prove (i) a bound on the loss that holds independent of any downstream task, as well as (ii) a criterion for robust classification in particular. We validate our theoretical results in practical applications, show how our results can be used for calibrating expectations of downstream robustness, and when our results are useful for optimal transfer learning. Taken together, our results offer an initial step towards characterizing the requirements of the representation function for reliable post-adaptation performance.
- 26 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Predictive Analysis of Optimal Automated Teller Machine Site Selection Using Machine Learning and Deep Learning: A Comprehensive Study on Variables, Challenges, and Opportunities
The proliferation of Automated Teller Machines (ATMs) in the banking sector has raised the stakes in identifying the most suitable locations for these machines, given their impact on the profitability and satisfaction of bank clients. This study presents a comprehensive examination of the variables that influence ATM placement, exploring the significance of identifying an optimal location and the challenges associated with this task. Our investigation pivots on market-centric variables such as the proximity of eateries, fuel stations, that are ubiquitously available in the public domain. To establish this benchmark, a dataset that remains singularly unique and is conspicuously absent from publicly accessible Internet repositories is created. Our innovative approach encompasses the application of multiple machine learning models to analyze the performance using unprecedented dataset. This study also focuses on ranking the market factors that we used in the novel dataset to study what market variables affect the location of an ATM along with resolving the limitations and challenges.
- 26 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Predictive Analysis of Optimal Automated Teller Machine Site Selection Using Machine Learning and Deep Learning: A Comprehensive Study on Variables, Challenges, and Opportunities
The proliferation of Automated Teller Machines (ATMs) in the banking sector has raised the stakes in identifying the most suitable locations for these machines, given their impact on the profitability and satisfaction of bank clients. This study presents a comprehensive examination of the variables that influence ATM placement, exploring the significance of identifying an optimal location and the challenges associated with this task. Our investigation pivots on market-centric variables such as the proximity of eateries, fuel stations, that are ubiquitously available in the public domain. To establish this benchmark, a dataset that remains singularly unique and is conspicuously absent from publicly accessible Internet repositories is created. Our innovative approach encompasses the application of multiple machine learning models to analyze the performance using unprecedented dataset. This study also focuses on ranking the market factors that we used in the novel dataset to study what market variables affect the location of an ATM along with resolving the limitations and challenges.