SK
Satyen Kale
cs.LGstat.MLmath.OCcs.DScs.AIcs.CLcs.DCcs.CRcs.DMcs.GT
On Valency
published · living versionsW_a7zea258·v1 · currentpublished
Contextual Bandit Learning with Predictable Rewards
with Alekh Agarwal, Miroslav Dudík, John Langford, Robert E. Schapire
1 version
W_zxxt5mf8·v1published
W_cut2ytv9·v1published
W_nkj8q39j·v1published
Preprints & journals
51 papers in the corpus · 2010–2026Faster Rates For Federated Variational Inequalities2602.09164v1 · Guanghui Wang, Satyen Kale2026 · 0 citationsarXiv
Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration2509.10439v2 · Ahmed Khaled, Satyen Kale, Arthur Douillard et al.2025 · 0 citationsarXiv
AdaBoN: Adaptive Best-of-N Alignment2505.12050v3 · Vinod Raman, Hilal Asi, Satyen Kale2025 · 0 citationsarXiv
Eager Updates For Overlapped Communication and Computation in DiLoCo2502.12996v1 · Satyen Kale, Arthur Douillard, Yanislav Donchev2025 · 0 citationsarXiv
Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch2501.18512v1 · Arthur Douillard, Yanislav Donchev, Keith Rush et al.2025 · 0 citationsarXiv
Stacking as Accelerated Gradient Descent2403.04978v2 · Naman Agarwal, Pranjal Awasthi, Satyen Kale et al.2024 · 0 citationsarXiv
Efficient Stagewise Pretraining via Progressive Subnetworks2402.05913v2 · Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu et al.2024 · 0 citationsarXiv
Asynchronous Local-SGD Training for Language Modeling2401.09135v2 · Bo Liu, Rachita Chhaparia, Arthur Douillard et al.2024 · 0 citationsarXiv
Improved Differentially Private and Lazy Online Convex Optimization2312.11534v2 · Naman Agarwal, Satyen Kale, Karan Singh et al.2023 · 0 citationsarXiv
Almost Tight Bounds for Differentially Private Densest Subgraph2308.10316v3 · Michael Dinitz, Satyen Kale, Silvio Lattanzi et al.2023 · 3 citationsarXiv
On the Convergence of Federated Averaging with Cyclic Client Participation2302.03109v1 · Yae Jee Cho, Pranay Sharma, Gauri Joshi et al.2023 · 11 citationsarXiv
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent2210.06705v1 · Satyen Kale, Jason D. Lee, Chris De Sa et al.2022 · 2 citationsarXiv
Private Matrix Approximation and Geometry of Unitary Orbits2207.02794v1 · Oren Mangoubi, Yikai Wu, Satyen Kale et al.2022 · 1 citationProceedings of Thirty Fifth Conference on Learning Theory (COLT), PMLR 178:3547-3588, 2022
Beyond Uniform Lipschitz Condition in Differentially Private Optimization2206.10713v2 · Rudrajit Das, Satyen Kale, Zheng Xu et al.2022 · 4 citationsarXiv
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data2206.04723v1 · Jianyu Wang, Rudrajit Das, Gauri Joshi et al.2022 · 18 citationsarXiv
Self-Consistency of the Fokker-Planck Equation2206.00860v2 · Zebang Shen, Zhenfu Wang, Satyen Kale et al.2022 · 8 citationsarXiv
Mixed Federated Learning: Joint Decentralized and Centralized Learning2205.13655v2 · Sean Augenstein, Andrew Hard, Lin Ning et al.2022 · 6 citationsarXiv
Reproducibility in Optimization: Theoretical Framework and Limits2202.04598v4 · Kwangjun Ahn, Prateek Jain, Ziwei Ji et al.2022 · 8 citationsarXiv
Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States2202.02765v1 · Julian Zimmert, Naman Agarwal, Satyen Kale2022 · 2 citationsarXiv
Agnostic Learnability of Halfspaces via Logistic Loss2201.13419v1 · Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi et al.2022 · 0 citationsarXiv
Efficient Methods for Online Multiclass Logistic Regression2110.03020v2 · Naman Agarwal, Satyen Kale, Julian Zimmert2021 · 4 citationsarXiv
A Field Guide to Federated Optimization2107.06917v1 · Jianyu Wang, Zachary Charles, Zheng Xu et al.2021 · 181 citationsarXiv
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs2107.05074v1 · Satyen Kale, Ayush Sekhari, Karthik Sridharan2021 · 1 citationarXiv
Federated Functional Gradient Boosting2103.06972v1 · Zebang Shen, Hamed Hassani, Satyen Kale et al.2021 · 5 citationsarXiv
A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness2103.01276v2 · Jacob Abernethy, Pranjal Awasthi, Satyen Kale2021 · 1 citationarXiv
Learning with User-Level Privacy2102.11845v3 · Daniel Levy, Ziteng Sun, Kareem Amin et al.2021 · 16 citationsarXiv
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning2008.03606v2 · Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale et al.2020 · 96 citationsarXiv
Estimating Training Data Influence by Tracing Gradient Descent2002.08484v3 · Garima Pruthi, Frederick Liu, Mukund Sundararajan et al.2020 · 127 citationsarXiv
A Deep Conditioning Treatment of Neural Networks2002.01523v3 · Naman Agarwal, Pranjal Awasthi, Satyen Kale2020 · 5 citationsarXiv
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning1910.06378v4 · Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri et al.2019 · 1,733 citationsarXiv
On the Convergence of Adam and Beyond1904.09237v1 · Sashank J. Reddi, Satyen Kale, Sanjiv Kumar2019 · 1,771 citationsarXivon Valency
Hypothesis Set Stability and Generalization1904.04755v3 · Dylan J. Foster, Spencer Greenberg, Satyen Kale et al.2019 · 13 citationsarXiv
Escaping Saddle Points with Adaptive Gradient Methods1901.09149v2 · Matthew Staib, Sashank J. Reddi, Satyen Kale et al.2019 · 49 citationsarXiv
Stochastic Negative Mining for Learning with Large Output Spaces1810.07076v1 · Sashank J. Reddi, Satyen Kale, Felix Yu et al.2018 · 30 citationsarXiv
Logistic Regression: The Importance of Being Improper1803.09349v2 · Dylan J. Foster, Satyen Kale, Haipeng Luo et al.2018 · 33 citationsarXiv
Parameter-free online learning via model selection1801.00101v2 · Dylan J. Foster, Satyen Kale, Mehryar Mohri et al.2017 · 24 citationsarXiv
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP1706.04690v1 · Satyen Kale, Zohar Karnin, Tengyuan Liang et al.2017 · 6 citationsProceedings of the 34th International Conference on Machine Learning 70 (2017) 1780-1788
Online Sparse Linear Regression1603.02250v1 · Dean Foster, Satyen Kale, Howard Karloff2016 · 4 citationsarXiv
Hardness of Online Sleeping Combinatorial Optimization Problems1509.03600v3 · Satyen Kale, Chansoo Lee, D'avid P'al2015 · 11 citationsarXiv
Online Gradient Boosting1506.04820v2 · Alina Beygelzimer, Elad Hazan, Satyen Kale et al.2015 · 51 citationsarXiv
Optimal and Adaptive Algorithms for Online Boosting1502.02651v1 · Alina Beygelzimer, Satyen Kale, Haipeng Luo2015 · 35 citationsarXivon Valency
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits1402.0555v2 · Alekh Agarwal, Daniel Hsu, Satyen Kale et al.2014 · 286 citationsarXivon Valency
Multiarmed Bandits With Limited Expert Advice1306.4653v4 · Satyen Kale2013 · 9 citationsarXiv
Bargaining for Revenue Shares on Tree Trading Networks1304.5822v1 · Arpita Ghosh, Satyen Kale, Kevin Lang et al.2013 · 3 citationsarXiv
Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization1206.6384v1 · Haim Avron, Satyen Kale, Shiva Kasiviswanathan et al.2012 · 51 citationsarXiv
Projection-free Online Learning1206.4657v1 · Elad Hazan (Technion), Satyen Kale2012 · 140 citationsarXivon Valency
Near-Optimal Algorithms for Online Matrix Prediction1204.0136v1 · Elad Hazan, Satyen Kale, Shai Shalev-Shwartz2012 · 45 citationsarXiv
Contextual Bandit Learning with Predictable Rewards1202.1334v2 · Alekh Agarwal, Miroslav Dud'ik, Satyen Kale et al.2012 · 43 citationsarXivon Valency
Efficient Optimal Learning for Contextual Bandits1106.2369v1 · Miroslav Dudik, Daniel Hsu, Satyen Kale et al.2011 · 174 citationsarXiv
Combinatorial Approximation Algorithms for MaxCut using Random Walks1008.3938v1 · Satyen Kale, C. Seshadhri2010 · 22 citationsarXiv
Career total: 143 works. 51 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.