Filter by type:

Sort by year:

Stochastic Negative Mining for Learning with Large Output Spaces

Sashank J. Reddi, Satyen Kale, Felix Yu, Daniel Holtmann-Rice, Jiecao Chen, Sanjiv Kumar
ConferenceProceedings of 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

Escaping Saddle Points with Adaptive Gradient Methods

Matthew Staib, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar, and Suvrit Sra
ConferenceProceedings of 36th International Conference on Machine Learning (ICML), 2019

Online Learning of Quantum States

Scott Aaronson, Xinyi Chen, Elad Hazan, Satyen Kale, and Ashwin Nayak
ConferenceProceedings of 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), 2018

On the convergence of Adam and Beyond

Sashank J. Reddi, Satyen Kale and Sanjiv Kumar
ConferenceProceedings of 6th International Conference on Learning Representations (ICLR), 2018

Loss Decomposition for Fast Learning in Large Output Spaces

Ian E.H. Yen, Satyen Kale, Felix X. Yu, Daniel Holtmann-Rice, Sanjiv Kumar and Pradeep Ravikumar
ConferenceProceedings of 35th International Conference on Machine Learning (ICML), 2018

Logistic Regression: The Importance of Being Improper

Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri and Karthik Sridharan
ConferenceProceedings of 31st Conference on Learning Theory (COLT), 2018

Adaptive Methods for Nonconvex Optimization

Manzil Zaheer, Sashank J. Reddi, Devendra Sachan, Satyen Kale, and Sanjiv Kumar
ConferenceProceedings of 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), 2018

Parameter-Free Online Learning via Model Selection

Dylan J. Foster, Satyen Kale, Mehryar Mohri and Karthik Sridharan
ConferenceProceedings of 31st Annual Conference on Neural Information Processing Systems (NeurIPS), 2017

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP

Satyen Kale, Zohar Karnin, Tengyuan Liang and Dávid Pál
ConferenceProceedings of 34th International Conference on Machine Learning (ICML), 2017

Online Sparse Linear Regression

Dean Foster, Satyen Kale, and Howard Karloff
ConferenceProceedings of 29th Conference on Learning Theory (COLT), 2016

Online Semidefinite Programming

Noa Elad, Satyen Kale and Joseph (Seffi) Naor
ConferenceProceedings of 43rd International Colloquium on Automata, Languages and Programming (ICALP), 2016

Hardness of Online Sleeping Combinatorial Optimization Problems.

Satyen Kale, Chansoo Lee and Dávid Pál
ConferenceProceedings of 30th Annual Conference on Neural Information Processing Systems (NeurIPS), 2016

Optimal and Adaptive Algorithms for Online Boosting

Alina Beygelzimer, Satyen Kale, and Haipeng Luo
ConferenceProceedings of 32nd International Conference on Machine Learning (ICML), 2015

Online Gradient Boosting

Alina Beygelzimer, Elad Hazan, Satyen Kale, and Haipeng Luo
ConferenceProceedings of 29th Annual Conference on Neural Information Processing Systems (NeurIPS), 2015

Budgeted Prediction With Expert Advice

Kareem Amin, Satyen Kale, Gerald Tesauro, and Deepak Turaga
ConferenceProceedings of 29th AAAI Conference on Artificial Intelligence (AAAI), 2015

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, and Robert E. Schapire
ConferenceProceedings of 31st International Conference on Machine Learning (ICML), 2014

Multiarmed Bandits With Limited Expert Advice

Satyen Kale
ConferenceProceedings of 27th Conference on Learning Theory (COLT), 2014

The Approximability of the Binary Paintshop Problem

Anupam Gupta, Satyen Kale, Viswanath Nagarajan, Rishi Saket, and Baruch Schieber
ConferenceProceedings of 16th International Workshop on Approximation Algorithms for Combinatorial Optimization Problems (APPROX), 2013

Bargaining for Revenue Shares on Tree Trading Networks

Arpita Ghosh, Satyen Kale, Kevin Lang, and Benjamin Moseley
ConferenceProceedings of 23rd International Conference on Artificial Intelligence (IJCAI), 2013

Adaptive Market Making via Online Learning

Jacob Abernethy and Satyen Kale
ConferenceProceedings of 27th Annual Conference on Neural Information Processing Systems (NeurIPS), 2013

The Multiplicative Weights Update Method: A Meta-Algorithm and Applications

Sanjeev Arora, Elad Hazan and Satyen Kale
JournalIn Theory of Computing , 2012

Projection-free Online Learning

Elad Hazan and Satyen Kale
ConferenceProceedings of 29th International Conference on Machine Learning (ICML), 2012

Near-Optimal Algorithms for Online Matrix Prediction

Elad Hazan, Satyen Kale and Shai Shalev-Shwartz
ConferenceJournalIn SIAM Journal on Computing (SICOMP), 2017. Proceedings of 25th Conference on Learning Theory (COLT), 2012

Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization

Haim Avron, Satyen Kale, Shiva Prasad Kasiviswanathan, and Vikas Sindhwani
ConferenceProceedings of 29th International Conference on Machine Learning (ICML), 2012

Contextual Bandit Learning with Predictable Rewards

Alekh Agarwal, Miroslav Dudik, Satyen Kale, John Langford and Robert E. Schapire
ConferenceProceedings of 15th International Conference on Artificial Intelligence and Statistics (AISTATS), 2012

Who Moderates the Moderators? Crowdsourcing Abuse Detection in User-generated Content

Arpita Ghosh, Satyen Kale, and R. Preston McAfee
ConferenceProceedings of 12th ACM Conference on Electronic Commerce (EC), 2011

Newtron: an Efficient Bandit algorithm for Online Multiclass Prediction

Elad Hazan and Satyen Kale
ConferenceProceedings of 27th Annual Conference on Neural Information Processing Systems (NeurIPS), 2011

Efficient optimal learning for contextual bandits

Miroslav Dudik, Daniel Hsu, Satyen Kale, Nikos Karampatziakis, John Langford, Lev Reyzin and Tong Zhang
ConferenceProceedings of 27th Conference on Uncertainty in Artificial Intelligence (UAI), 2011

Cross-Validation and Mean-Square Stability

Satyen Kale, Ravi Kumar, and Sergei Vassilvitskii
ConferenceProceedings of 2nd Symposium on Innovations in Computer Science (ICS), 2011

Combinatorial Approximation Algorithms for MaxCut using Random Walks

Satyen Kale and C. Seshadhri
ConferenceProceedings of 2nd Symposium on Innovations in Computer Science (ICS), 2011

Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization

Elad Hazan and Satyen Kale
ConferenceJournalIn Journal of Machine Learning Research (JMLR), 2014. Also in proceedings of 24th Conference on Learning Theory (COLT), 2011

Non-Stochastic Bandit Slate Problems

Satyen Kale, Lev Reyzin, and Robert E. Schapire
ConferenceProceedings of 24th Annual Conference on Neural Information Processing Systems (NeurIPS), 2010

Learning rotations with little regret

Elad Hazan, Satyen Kale, and Manfred K. Warmuth
ConferenceJournalIn Machine Learning Journal (MLJ), (2016). Also in proceedings of 23rd Conference on Learning Theory (COLT), 2010. Corrigendum to conference version, 2010

The Uniform Hardcore Lemma via Approximate Bregman Projections

Boaz Barak, Moritz Hardt and Satyen Kale
ConferenceTech ReportAppeared as ECCC Report TR07-131 and in proceedings of 20th ACM-SIAM Symposium on Discrete Algorithms (SODA), 2009

Online Submodular Minimization

Elad Hazan and Satyen Kale
ConferenceJournalIn Journal of Machine Learning Research (JMLR), 2012. Also in proceedings of 23rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2009

Better Algorithms for Benign Bandits

Elad Hazan and Satyen Kale
ConferenceJournalIn Journal of Machine Learning Research (JMLR), 2011. Also in proceedings of 20th ACM-SIAM Symposium on Discrete Algorithms (SODA), 2009

An online portfolio selection algorithm with regret logarithmic in price variation

Elad Hazan and Satyen Kale
ConferenceJournalIn Mathematical Finance, 2012. Originally appeared as "On Stochastic and Worst-case Models for Investing" in proceedings of 23rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2009

Noise Tolerance of Expanders and Sublinear Expander Reconstruction

Satyen Kale, Yuval Peres and C. Seshadhri
ConferenceJournalIn SIAM Journal on Computing (SICOMP), 2014. Also in proceedings of 49th Annual IEEE Symposium on Foundations of Computer Science (FOCS), 2008

Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs

Elad Hazan and Satyen Kale
ConferenceJournalIn Machine Learning Journal (MLJ), 2010. Also in proceedings of 21st Conference on Learning Theory (COLT), 2008

An Expansion Tester for Bounded Degree Graphs

Satyen Kale and C. Seshadhri
ConferenceJournalTech ReportIn SIAM Journal on Computing (SICOMP), 2011. Also appeared as ECCC Report TR07-131 and in proceedings of 35th International Colloquium on Automata, Languages and Programming (ICALP), 2008

Privacy, Accuracy, and Consistency Too: A Holistic Solution to Contingency Table Release

Boaz Barak, Kamalika Chaudhuri, Cynthia Dwork, Satyen Kale, Frank McSherry and Kunal Talwar
ConferenceProceedings of 26th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems (PODS), 2007

Efficient Algorithms using the Multiplicative Weights Update Method

Satyen Kale
Tech ReportPh.D. thesis. Princeton Tech Report TR-804-07, 2007

Computational Equivalence of Fixed Points and No Regret Algorithms, and Convergence to Equilibria

Elad Hazan and Satyen Kale
ConferenceProceedings of 21st Annual Conference on Neural Information Processing Systems (NeurIPS), 2007

A Combinatorial, Primal-Dual approach to Semidefinite Programs

Sanjeev Arora and Satyen Kale
ConferenceJournalIn Journal of the ACM, 2016. Also in proceedings of 39th ACM Symposium on Theory of Computing (STOC), 2007

Logarithmic Regret Algorithms for Online Convex Optimization

Elad Hazan, Amit Agarwal and Satyen Kale
ConferenceJournalIn Machine Learning Journal (MLJ), 2007. An earlier version with Adam Kalai appeared in proceedings of 19th Conference on Learning Theory (COLT), 2006

Efficient Aggregation Algorithms for Probabilistic Data

T. S. Jayram, Satyen Kale and Erik Vee
ConferenceProceedings of 18th ACM-SIAM Symposium on Discrete Algorithms (SODA), 2006

Algorithms for Portfolio Management based on the Newton Method

Amit Agarwal, Elad Hazan, Satyen Kale and Robert Schapire
ConferenceProceedings of 23rd International Conference on Machine Learning (ICML), 2006

A Variation on SVD Based Image Compression

Abhiram Ranade, Srikanth S. M. and Satyen Kale
ConferenceJournalIn Image and Vision Computing, 2007. In proceedings of 3rd Workshop on Computer Vision, Graphics, and Image Processing (WCVGIP), 2006

A Fast Random Sampling Algorithm for Sparsifying Matrices

Sanjeev Arora, Elad Hazan and Satyen Kale
ConferenceProceedings of 10th International Workshop on Approximation Algorithms for Combinatorial Optimization Problems (APPROX), 2006

Fast Algorithms for Approximate Semidefinite Programming using the Multiplicative Weights Update method

Sanjeev Arora, Elad Hazan and Satyen Kale
ConferenceProceedings of 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS), 2005

Analysis and Algorithms for Content-based Event Matching

Satyen Kale, Elad Hazan, Fengyun Cao and Jaswinder Pal Singh
ConferenceProceedings of 4th International Workshop on Distributed Event-Based Systems (DEBS), 2005

Approximating Quadratic Programs with Positive Semidefinite Constraints

Elad Hazan and Satyen Kale
Tech ReportPrinceton Tech Report TR-746-06, 2004

\(O(\sqrt{\log n})\) approximation to SPARSEST CUT in \(\tilde{O}(n^2)\) time

Sanjeev Arora, Elad Hazan and Satyen Kale
ConferenceJournalIn SIAM Journal on Computing (SICOMP), 2010. Also in proceedings of 45th Annual IEEE Symposium on Foundations of Computer Science (FOCS), 2004