Krishna Pillutla

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 31

Top Topics

Sample Complexity

Heterogeneous Data

Differentially Private

Top Venues

Publications

Zachary Charles, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, Nicole Mitchell, Krishna Pillutla, Keith Rush
Fine-Tuning Large Language Models with User-Level Differential Privacy. CoRR (2024)
Christopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. ICLR (2024)
Krishna Pillutla, Yassine Laguel, Jérôme Malick, Zaïd Harchaoui
Federated learning with superquantile aggregation for heterogeneous data. Mach. Learn. 113 (5) (2024)
Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakurta
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy. CoRR (2024)
Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zaïd Harchaoui
Distributionally Robust Optimization with Bias and Variance Reduction. ICLR (2024)
Zachary Charles, Nicole Mitchell, Krishna Pillutla, Michael Reneer, Zachary Garrett
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning. NeurIPS (2023)
Krishna Pillutla, Galen Andrew, Peter Kairouz, H. Brendan McMahan, Alina Oprea, Sewoong Oh
Unleashing the Power of Randomization in Auditing Differentially Private ML. CoRR (2023)
Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zaïd Harchaoui
Distributionally Robust Optimization with Bias and Variance Reduction. CoRR (2023)
Krishna Pillutla, Galen Andrew, Peter Kairouz, H. Brendan McMahan, Alina Oprea, Sewoong Oh
Unleashing the Power of Randomization in Auditing Differentially Private ML. NeurIPS (2023)
Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu
User Inference Attacks on Large Language Models. CoRR (2023)
Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
Modified Gauss-Newton Algorithms under Noise. CoRR (2023)
Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
Modified Gauss-Newton Algorithms under Noise. SSP (2023)
Zachary Charles, Nicole Mitchell, Krishna Pillutla, Michael Reneer, Zachary Garrett
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning. CoRR (2023)
Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zaïd Harchaoui
Influence Diagnostics under Self-concordance. AISTATS (2023)
Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zaïd Harchaoui
Stochastic Optimization for Spectral Risk Measures. AISTATS (2023)
Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. CoRR (2023)
Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao
Federated Learning with Partial Model Personalization. CoRR (2022)
Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
MAUVE Scores for Generative Models: Theory and Practice. CoRR (2022)
Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao
Federated Learning with Partial Model Personalization. ICML (2022)
Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zaïd Harchaoui
Statistical and Computational Guarantees for Influence Diagnostics. CoRR (2022)
Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zaïd Harchaoui
Stochastic Optimization for Spectral Risk Measures. CoRR (2022)
Krishna Pillutla, Sham M. Kakade, Zaïd Harchaoui
Robust Aggregation for Federated Learning. IEEE Trans. Signal Process. 70 (2022)
Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. CoRR (2021)
Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaïd Harchaoui
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers. NeurIPS (2021)
Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. NeurIPS (2021)
Yassine Laguel, Krishna Pillutla, Jérôme Malick, Zaïd Harchaoui
A Superquantile Approach to Federated Learning with Heterogeneous Devices. CISS (2021)
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals. NeurIPS (2021)
Krishna Pillutla, Yassine Laguel, Jérôme Malick, Zaïd Harchaoui
Federated Learning with Heterogeneous Data: A Superquantile Optimization Approach. CoRR (2021)
Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Yejin Choi, Zaïd Harchaoui
MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation. CoRR (2021)
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral. CoRR (2021)
Yassine Laguel, Krishna Pillutla, Jérôme Malick, Zaïd Harchaoui
Device Heterogeneity in Federated Learning: A Superquantile Approach. CoRR (2020)