Прати
Krishna Pillutla
Krishna Pillutla
Верификована је имејл адреса на iitm.ac.in - Почетна страница
Наслов
Навело
Навело
Година
Robust Aggregation for Federated Learning
K Pillutla, SM Kakade, Z Harchaoui
IEEE Transactions on Signal Processing 70, 1142-1154, 2022
7402022
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
K Pillutla, S Swayamdipta, R Zellers, J Thickstun, S Welleck, Y Choi, ...
Advances in Neural Information Processing Systems 34, 4816-4828, 2021
3362021
Federated Learning with Partial Model Personalization
K Pillutla, K Malik, AR Mohamed, M Rabbat, M Sanjabi, L Xiao
International Conference on Machine Learning, 17716-17758, 2022
1852022
Federated Learning with Superquantile Aggregation for Heterogeneous Data
K Pillutla, Y Laguel, J Malick, Z Harchaoui
Machine Learning, 1-68, 2023
91*2023
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)
P Jain, SM Kakade, R Kidambi, P Netrapalli, VK Pillutla, A Sidford
arXiv preprint arXiv:1710.09430, 2017
442017
User Inference Attacks on Large Language Models
N Kandpal, K Pillutla, A Oprea, P Kairouz, CA Choquette-Choo, Z Xu
arXiv preprint arXiv:2310.09266, 2023
30*2023
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
Z Charles, N Mitchell, K Pillutla, M Reneer, Z Garrett
Advances in Neural Information Processing Systems 36, 2023
262023
Unleashing the Power of Randomization in Auditing Differentially Private ML
K Pillutla, G Andrew, P Kairouz, HB McMahan, A Oprea, S Oh
Advances in Neural Information Processing Systems 36, 2023
262023
Superquantiles at work: Machine learning applications and efficient subgradient computation
Y Laguel, K Pillutla, J Malick, Z Harchaoui
Set-Valued and Variational Analysis 29 (4), 967-996, 2021
242021
A Smoother Way to Train Structured Prediction Models
VK Pillutla, V Roulet, SM Kakade, Z Harchaoui
Advances in Neural Information Processing Systems 31, 2018
242018
Influence diagnostics under self-concordance
J Fisher, L Liu, K Pillutla, Y Choi, Z Harchaoui
International Conference on Artificial Intelligence and Statistics, 10028-10076, 2023
21*2023
MAUVE Scores for Generative Models: Theory and Practice
K Pillutla, L Liu, J Thickstun, S Welleck, S Swayamdipta, R Zellers, S Oh, ...
Journal of Machine Learning Research 24 (356), 1-92, 2023
192023
Data driven resource allocation for distributed learning
T Dick, M Li, VK Pillutla, C White, N Balcan, A Smola
Artificial Intelligence and Statistics, 662-671, 2017
172017
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
CA Choquette-Choo, K Dvijotham, K Pillutla, A Ganesh, T Steinke, ...
International Conference on Learning Representations, 2024
162024
Divergence frontiers for generative models: Sample complexity, quantization effects, and frontier integrals
L Liu, K Pillutla, S Welleck, S Oh, Y Choi, Z Harchaoui
Advances in Neural Information Processing Systems 34, 12930-12942, 2021
152021
Fine-tuning large language models with user-level differential privacy
Z Charles, A Ganesh, R McKenna, HB McMahan, N Mitchell, K Pillutla, ...
arXiv preprint arXiv:2407.07737, 2024
132024
Stochastic optimization for spectral risk measures
R Mehta, V Roulet, K Pillutla, L Liu, Z Harchaoui
International Conference on Artificial Intelligence and Statistics, 10112-10159, 2023
122023
LLC: Accurate, multi-purpose learnt low-dimensional binary codes
A Kusupati, M Wallingford, V Ramanujan, R Somani, JS Park, K Pillutla, ...
Advances in neural information processing systems 34, 23900-23913, 2021
122021
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
K Dvijotham, HB McMahan, K Pillutla, T Steinke, A Thakurta
arXiv preprint arXiv:2404.16706, 2024
102024
Reconstructing cancer drug response networks using multitask learning
M Ruffalo, P Stojanov, VK Pillutla, R Varma, Z Bar-Joseph
BMC Systems Biology 11, 1-15, 2017
92017
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–20