Clik here to view.
Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin...
Pritish Kamath, Omar Montasser, Nathan Srebro: Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity. COLT 2020: 2236-2262
View ArticleClik here to view.
On the Complexity of Modulo-q Arguments and the Chevalley - Warning Theorem.
Mika Göös, Pritish Kamath, Katerina Sotiraki, Manolis Zampetakis: On the Complexity of Modulo-q Arguments and the Chevalley - Warning Theorem. CCC 2020: 19:1-19:42
View ArticleClik here to view.
Monotone Circuit Lower Bounds from Resolution.
Ankit Garg, Mika Göös, Pritish Kamath, Dmitry Sokolov: Monotone Circuit Lower Bounds from Resolution. Theory Comput. 16: 1-30 (2020)
View ArticleClik here to view.
Optimality of Correlated Sampling Strategies.
Mohammad Bavarian, Badih Ghazi, Elad Haramaty, Pritish Kamath, Ronald L. Rivest, Madhu Sudan: Optimality of Correlated Sampling Strategies. Theory Comput. 16: 1-18 (2020)
View ArticleClik here to view.
On the Power of Differentiable Learning versus PAC and SQ Learning.
Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro: On the Power of Differentiable Learning versus PAC and SQ Learning. CoRR abs/2108.04190 (2021)
View ArticleClik here to view.
Supervised Bayesian Specification Inference from Demonstrations.
Ankit J. Shah, Pritish Kamath, Shen Li, Patrick L. Craven, Kevin J. Landers, Kevin Oden, Julie Shah: Supervised Bayesian Specification Inference from Demonstrations. CoRR abs/2107.02912 (2021)
View ArticleClik here to view.
Eluder Dimension and Generalized Rank.
Gene Li, Pritish Kamath, Dylan J. Foster, Nathan Srebro: Eluder Dimension and Generalized Rank. CoRR abs/2104.06970 (2021)
View ArticleClik here to view.
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels.
Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro: Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels. CoRR abs/2103.01210 (2021)
View ArticleClik here to view.
Does Invariant Risk Minimization Capture Invariance?
Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro: Does Invariant Risk Minimization Capture Invariance? CoRR abs/2101.01134 (2021)
View ArticleClik here to view.
On the Power of Differentiable Learning versus PAC and SQ Learning.
Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro: On the Power of Differentiable Learning versus PAC and SQ Learning. NeurIPS 2021: 24340-24351
View ArticleClik here to view.
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels.
Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro: Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels. ICML 2021: 7379-7389
View ArticleClik here to view.
Does Invariant Risk Minimization Capture Invariance?
Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro: Does Invariant Risk Minimization Capture Invariance? AISTATS 2021: 4069-4077
View ArticleClik here to view.
Circuits Resilient to Short-Circuit Errors.
Klim Efremenko, Bernhard Haeupler, Yael Kalai, Pritish Kamath, Gillat Kol, Nicolas Resch, Raghuvansh Saxena: Circuits Resilient to Short-Circuit Errors. Electron. Colloquium Comput. Complex. TR22 (2022)
View ArticleClik here to view.
On Differentially Private Counting on Trees.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Kewen Wu: On Differentially Private Counting on Trees. CoRR abs/2212.11967 (2022)
View ArticleClik here to view.
Regression with Label Differential Privacy.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang: Regression with Label Differential Privacy. CoRR abs/2212.06074 (2022)
View ArticleClik here to view.
Private Ad Modeling with DP-SGD.
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang: Private Ad Modeling with DP-SGD. CoRR abs/2211.11896...
View ArticleClik here to view.
Anonymized Histograms in Intermediate Privacy Models.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Anonymized Histograms in Intermediate Privacy Models. CoRR abs/2210.15178 (2022)
View ArticleClik here to view.
Private Isotonic Regression.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Private Isotonic Regression. CoRR abs/2210.15175 (2022)
View ArticleClik here to view.
Faster Privacy Accounting via Evolving Discretization.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Faster Privacy Accounting via Evolving Discretization. CoRR abs/2207.04381 (2022)
View ArticleClik here to view.
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions.
Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions. CoRR abs/2207.04380 (2022)
View ArticleClik here to view.
Do More Negative Samples Necessarily Hurt in Contrastive Learning?
Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath: Do More Negative Samples Necessarily Hurt in Contrastive Learning? CoRR abs/2205.01789 (2022)
View ArticleClik here to view.
Circuits resilient to short-circuit errors.
Klim Efremenko, Bernhard Haeupler, Yael Tauman Kalai, Pritish Kamath, Gillat Kol, Nicolas Resch, Raghuvansh R. Saxena: Circuits resilient to short-circuit errors. STOC 2022: 582-594
View ArticleClik here to view.
Understanding the Eluder Dimension.
Gene Li, Pritish Kamath, Dylan J. Foster, Nati Srebro: Understanding the Eluder Dimension. NeurIPS 2022
View ArticleClik here to view.
Private Isotonic Regression.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Private Isotonic Regression. NeurIPS 2022
View ArticleClik here to view.
Anonymized Histograms in Intermediate Privacy Models.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Anonymized Histograms in Intermediate Privacy Models. NeurIPS 2022
View ArticleClik here to view.
Faster Privacy Accounting via Evolving Discretization.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Faster Privacy Accounting via Evolving Discretization. ICML 2022: 7470-7483
View ArticleClik here to view.
Do More Negative Samples Necessarily Hurt In Contrastive Learning?
Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath: Do More Negative Samples Necessarily Hurt In Contrastive Learning? ICML 2022: 1101-1116
View ArticleClik here to view.
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions.
Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions. Proc. Priv. Enhancing Technol. 2022(4):...
View ArticleClik here to view.
Limits on the Efficiency of (Ring) LWE-Based Non-interactive Key Exchange.
Siyao Guo, Pritish Kamath, Alon Rosen, Katerina Sotiraki: Limits on the Efficiency of (Ring) LWE-Based Non-interactive Key Exchange. J. Cryptol. 35(1): 1 (2022)
View ArticleClik here to view.
Optimal Unbiased Randomizers for Regression with Label Differential Privacy.
Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang: Optimal Unbiased Randomizers for Regression with Label...
View ArticleClik here to view.
Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API.
Hidayet Aksu, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon, Avinash V. Varadarajan: Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API. CoRR...
View ArticleClik here to view.
Sparsity-Preserving Differentially Private Training of Large Embedding Models.
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang: Sparsity-Preserving Differentially Private Training of Large Embedding Models. CoRR abs/2311.08357...
View ArticleClik here to view.
User-Level Differential Privacy With Few Examples Per User.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang: User-Level Differential Privacy With Few Examples Per User. CoRR abs/2309.12500 (2023)
View ArticleClik here to view.
Optimizing Hierarchical Queries for the Attribution Reporting API.
Matthew Dawson, Badih Ghazi, Pritish Kamath, Kapil Kumar, Ravi Kumar, Bo Luan, Pasin Manurangsi, Nishanth Mundru, Harikesh Nair, Adam Sealfon, Shengyu Zhu: Optimizing Hierarchical Queries for the...
View ArticleClik here to view.
Ticketed Learning-Unlearning Schemes.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang: Ticketed Learning-Unlearning Schemes. CoRR abs/2306.15744 (2023)
View ArticleClik here to view.
On User-Level Private Convex Optimization.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Raghu Meka, Pasin Manurangsi, Chiyuan Zhang: On User-Level Private Convex Optimization. CoRR abs/2305.04912 (2023)
View ArticleClik here to view.
Separating Computational and Statistical Differential Privacy (Under...
Badih Ghazi, Rahul Ilango, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Separating Computational and Statistical Differential Privacy (Under Plausible Assumptions). CoRR abs/2301.00104 (2023)
View ArticleClik here to view.
On User-Level Private Convex Optimization.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang: On User-Level Private Convex Optimization. ICML 2023: 11283-11299
View ArticleClik here to view.
Regression with Label Differential Privacy.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang: Regression with Label Differential Privacy. ICLR 2023
View ArticleClik here to view.
On Differentially Private Counting on Trees.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Kewen Wu: On Differentially Private Counting on Trees. ICALP 2023: 66:1-66:18
View ArticleClik here to view.
Towards Separating Computational and Statistical Differential Privacy.
Badih Ghazi, Rahul Ilango, Pritish Kamath, Ravi Kumar, Pasin Manurangsi: Towards Separating Computational and Statistical Differential Privacy. FOCS 2023: 580-599
View ArticleClik here to view.
Ticketed Learning-Unlearning Schemes.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang: Ticketed Learning-Unlearning Schemes. COLT 2023: 5110-5139
View ArticleClik here to view.
Private Ad Modeling with DP-SGD.
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang: Private Ad Modeling with DP-SGD. AdKDD@KDD 2023
View ArticleClik here to view.
Optimizing Hierarchical Queries for the Attribution Reporting API.
Matthew Dawson, Badih Ghazi, Pritish Kamath, Kapil Kumar, Ravi Kumar, Bo Luan, Pasin Manurangsi, Nishanth Mundru, Harikesh Nair, Adam Sealfon, Shengyu Zhu: Optimizing Hierarchical Queries for the...
View ArticleClik here to view.
Supervised Bayesian specification inference from demonstrations.
Ankit Shah, Pritish Kamath, Shen Li, Patrick L. Craven, Kevin J. Landers, Kevin Oden, Julie Shah: Supervised Bayesian specification inference from demonstrations. Int. J. Robotics Res. 42(14):...
View ArticleClik here to view.
Training Differentially Private Ad Prediction Models with Semi-Sensitive...
Lynn Chua, Qiliang Cui, Badih Ghazi, Charlie Harrison, Pritish Kamath, Walid Krichene, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang: Training...
View ArticleClik here to view.
Optimal Unbiased Randomizers for Regression with Label Differential Privacy.
Ashwinkumar Badanidiyuru Varadaraja, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang: Optimal Unbiased Randomizers for Regression with...
View ArticleClik here to view.
On Computing Pairwise Statistics with Local Differential Privacy.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon: On Computing Pairwise Statistics with Local Differential Privacy. NeurIPS 2023
View ArticleClik here to view.
User-Level Differential Privacy With Few Examples Per User.
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang: User-Level Differential Privacy With Few Examples Per User. NeurIPS 2023
View ArticleClik here to view.
Sparsity-Preserving Differentially Private Training of Large Embedding Models.
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang: Sparsity-Preserving Differentially Private Training of Large Embedding Models. NeurIPS 2023
View Article
