Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPeter L. Bartlett
Person information
- affiliation: University of California at Berkeley, Department of Statistics, CA, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[c135]Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit. ALT 2023: 1166-1215- [i89]Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro:
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks. CoRR abs/2303.01456 (2023) - [i88]Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro:
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization. CoRR abs/2303.01462 (2023) - [i87]Peter L. Bartlett, Philip M. Long:
Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions. CoRR abs/2304.11059 (2023) - 2022
- [c134]Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, Michael I. Jordan:
Optimal Mean Estimation without a Variance. COLT 2022: 356-357 - [c133]Peter L. Bartlett, Piotr Indyk, Tal Wagner:
Generalization Bounds for Data-Driven Numerical Linear Algebra. COLT 2022: 2013-2040 - [c132]Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett:
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation. COLT 2022: 2060-2061 - [c131]Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett:
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. COLT 2022: 2668-2703 - [i86]Wenlong Mou, Koulik Khamaru, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
Optimal variance-reduced stochastic approximation in Banach spaces. CoRR abs/2201.08518 (2022) - [i85]Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett:
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. CoRR abs/2202.05928 (2022) - [i84]Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett:
Random Feature Amplification: Feature Learning and Generalization in Neural Networks. CoRR abs/2202.07626 (2022) - [i83]Juan C. Perdomo, Akshay Krishnamurthy, Peter L. Bartlett, Sham M. Kakade:
A Sharp Characterization of Linear Estimators for Offline Policy Evaluation. CoRR abs/2203.04236 (2022) - [i82]Peter L. Bartlett, Piotr Indyk, Tal Wagner:
Generalization Bounds for Data-Driven Numerical Linear Algebra. CoRR abs/2206.07886 (2022) - [i81]Aldo Pacchiano, Ofir Nachum, Nilesh Tripuraneni, Peter L. Bartlett:
Joint Representation Training in Sequential Tasks with Shared Structure. CoRR abs/2206.12441 (2022) - [i80]Wenlong Mou, Martin J. Wainwright, Peter L. Bartlett:
Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency. CoRR abs/2209.13075 (2022) - [i79]Peter L. Bartlett, Philip M. Long, Olivier Bousquet:
The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. CoRR abs/2210.01513 (2022) - [i78]Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu:
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data. CoRR abs/2210.07082 (2022) - 2021
- [j55]Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin:
Deep learning: a statistical viewpoint. Acta Numer. 30: 87-201 (2021) - [j54]Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm. J. Mach. Learn. Res. 22: 42:1-42:41 (2021) - [j53]Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett:
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? J. Mach. Learn. Res. 22: 159:1-159:48 (2021) - [j52]Peter L. Bartlett, Philip M. Long:
Failures of Model-dependent Generalization Bounds for Least-norm Interpolation. J. Mach. Learn. Res. 22: 204:1-204:15 (2021) - [c130]Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett, Heinrich Jiang:
Stochastic Bandits with Linear Constraints. AISTATS 2021: 2827-2835 - [c129]Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett:
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021: 927-1027 - [c128]Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett:
Towards a Dimension-Free Understanding of Adaptive Linear Control. COLT 2021: 3681-3770 - [c127]Raman Arora, Peter L. Bartlett, Poorya Mianjy, Nathan Srebro:
Dropout: Explicit Forms and Capacity Control. ICML 2021: 351-361 - [c126]Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt:
Agnostic Learning with Unknown Utilities. ITCS 2021: 55:1-55:20 - [c125]Aldo Pacchiano, Jonathan N. Lee, Peter L. Bartlett, Ofir Nachum:
Near Optimal Policy Optimization via REPS. NeurIPS 2021: 1100-1110 - [c124]Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
On the Theory of Reinforcement Learning with Once-per-Episode Feedback. NeurIPS 2021: 3401-3412 - [c123]Peter L. Bartlett, Sébastien Bubeck, Yeshwanth Cherapanamjeri:
Adversarial Examples in Multi-Layer Random ReLU Networks. NeurIPS 2021: 9241-9252 - [i77]Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett:
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? CoRR abs/2102.04998 (2021) - [i76]Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin:
Deep learning: a statistical viewpoint. CoRR abs/2103.09177 (2021) - [i75]Aldo Pacchiano, Jonathan N. Lee, Peter L. Bartlett, Ofir Nachum:
Near Optimal Policy Optimization via REPS. CoRR abs/2103.09756 (2021) - [i74]Lin Chen, Bruno Scherrer, Peter L. Bartlett:
Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm. CoRR abs/2103.09847 (2021) - [i73]Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett:
Towards a Dimension-Free Understanding of Adaptive Linear Control. CoRR abs/2103.10620 (2021) - [i72]Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt:
Agnostic learning with unknown utilities. CoRR abs/2104.08482 (2021) - [i71]Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright:
Preference learning along multiple criteria: A game-theoretic perspective. CoRR abs/2105.01850 (2021) - [i70]Jeffrey Chan, Aldo Pacchiano, Nilesh Tripuraneni, Yun S. Song, Peter L. Bartlett, Michael I. Jordan:
Parallelizing Contextual Linear Bandits. CoRR abs/2105.10590 (2021) - [i69]Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
On the Theory of Reinforcement Learning with Once-per-Episode Feedback. CoRR abs/2105.14363 (2021) - [i68]Peter L. Bartlett, Sébastien Bubeck, Yeshwanth Cherapanamjeri:
Adversarial Examples in Multi-Layer Random ReLU Networks. CoRR abs/2106.12611 (2021) - [i67]Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett:
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. CoRR abs/2108.11489 (2021) - [i66]Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit. CoRR abs/2111.04873 (2021) - [i65]Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett:
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation. CoRR abs/2112.12770 (2021) - 2020
- [j51]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. J. Mach. Learn. Res. 21: 21:1-21:51 (2020) - [c122]Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett:
Langevin Monte Carlo without smoothness. AISTATS 2020: 1716-1726 - [c121]Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett:
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits. AISTATS 2020: 1844-1854 - [c120]Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration. COLT 2020: 2947-2997 - [c119]Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan:
Stochastic Gradient and Langevin Processes. ICML 2020: 1810-1819 - [c118]Jonathan N. Lee, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
Accelerated Message Passing for Entropy-Regularized MAP Inference. ICML 2020: 5736-5746 - [c117]Eric Mazumdar, Aldo Pacchiano, Yi-An Ma, Michael I. Jordan, Peter L. Bartlett:
On Approximate Thompson Sampling with Langevin Algorithms. ICML 2020: 6797-6807 - [c116]Thanh Tan Nguyen, Nan Ye, Peter L. Bartlett:
Greedy Convex Ensemble. IJCAI 2020: 3101-3107 - [c115]Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright:
Preference learning along multiple criteria: A game-theoretic perspective. NeurIPS 2020 - [c114]Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett:
Self-Distillation Amplifies Regularization in Hilbert Space. NeurIPS 2020 - [i64]Niladri S. Chatterji, Peter L. Bartlett, Philip M. Long:
Oracle lower bounds for stochastic gradient sampling algorithms. CoRR abs/2002.00291 (2020) - [i63]Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett:
Self-Distillation Amplifies Regularization in Hilbert Space. CoRR abs/2002.05715 (2020) - [i62]Eric Mazumdar, Aldo Pacchiano, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan:
On Thompson Sampling with Langevin Algorithms. CoRR abs/2002.10002 (2020) - [i61]Raman Arora, Peter L. Bartlett, Poorya Mianjy, Nathan Srebro:
Dropout: Explicit Forms and Capacity Control. CoRR abs/2003.03397 (2020) - [i60]Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration. CoRR abs/2004.04719 (2020) - [i59]Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett, Heinrich Jiang:
Stochastic Bandits with Linear Constraints. CoRR abs/2006.10185 (2020) - [i58]Jonathan N. Lee, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan:
Accelerated Message Passing for Entropy-Regularized MAP Inference. CoRR abs/2007.00699 (2020) - [i57]Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni, Michael I. Jordan, Nicolas Flammarion, Peter L. Bartlett:
Optimal Robust Linear Regression in Nearly Linear Time. CoRR abs/2007.08137 (2020) - [i56]Peter L. Bartlett, Philip M. Long:
Failures of model-dependent generalization bounds for least-norm interpolation. CoRR abs/2010.08479 (2020) - [i55]Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, Michael I. Jordan:
Optimal Mean Estimation without a Variance. CoRR abs/2011.12433 (2020) - [i54]Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett:
When does gradient descent with logistic loss find interpolating two-layer networks? CoRR abs/2012.02409 (2020) - [i53]Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter L. Bartlett:
Regret Bound Balancing and Elimination for Model Selection in Bandits and RL. CoRR abs/2012.13045 (2020)
2010 – 2019
- 2019
- [j50]Peter L. Bartlett, Nick Harvey, Christopher Liaw, Abbas Mehrabian:
Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks. J. Mach. Learn. Res. 20: 63:1-63:17 (2019) - [j49]Peter L. Bartlett, David P. Helmbold, Philip M. Long:
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks. Neural Comput. 31(3) (2019) - [c113]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. AISTATS 2019: 2916-2925 - [c112]Vidya Muthukumar, Mitas Ray, Anant Sahai, Peter L. Bartlett:
Best of many worlds: Robust model selection for online supervised learning. AISTATS 2019: 3177-3186 - [c111]Peter L. Bartlett, Victor Gabillon, Michal Valko:
A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. ALT 2019: 184-206 - [c110]Yeshwanth Cherapanamjeri, Peter L. Bartlett:
Testing Symmetric Markov Chains Without Hitting. COLT 2019: 758-785 - [c109]Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett:
Fast Mean Estimation with Sub-Gaussian Rates. COLT 2019: 786-806 - [c108]Peter L. Bartlett, Victor Gabillon, Jennifer Healey, Michal Valko:
Scale-free adaptive planning for deterministic dynamics & discounted rewards. ICML 2019: 495-504 - [c107]Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett:
Online learning with kernel losses. ICML 2019: 971-980 - [c106]Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz:
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction. ICML 2019: 3692-3702 - [c105]Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett:
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning. ICML 2019: 7074-7084 - [c104]Dong Yin, Kannan Ramchandran, Peter L. Bartlett:
Rademacher Complexity for Adversarially Robust Generalization. ICML 2019: 7085-7094 - [i52]Yasin Abbasi-Yadkori, Peter L. Bartlett, Xi Chen, Alan Malek:
Large-Scale Markov Decision Problems via the Linear Programming Dual. CoRR abs/1901.01992 (2019) - [i51]Xiang Cheng, Peter L. Bartlett, Michael I. Jordan:
Quantitative Central Limit Theorems for Discrete Stochastic Processes. CoRR abs/1902.00832 (2019) - [i50]Yi-An Ma, Niladri S. Chatterji, Xiang Cheng, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan:
Is There an Analog of Nesterov Acceleration for MCMC? CoRR abs/1902.00996 (2019) - [i49]Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett:
Fast Mean Estimation with Sub-Gaussian Rates. CoRR abs/1902.01998 (2019) - [i48]Yeshwanth Cherapanamjeri, Peter L. Bartlett:
Testing Markov Chains without Hitting. CoRR abs/1902.01999 (2019) - [i47]Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett:
OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits. CoRR abs/1905.10040 (2019) - [i46]Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett:
Langevin Monte Carlo without Smoothness. CoRR abs/1905.13285 (2019) - [i45]Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler:
Benign Overfitting in Linear Regression. CoRR abs/1906.11300 (2019) - [i44]Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan:
Quantitative W1 Convergence of Langevin-Like Stochastic Processes with Non-Convex Potential State-Dependent Noise. CoRR abs/1907.03215 (2019) - [i43]Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, Michael I. Jordan:
Bayesian Robustness: A Nonasymptotic Viewpoint. CoRR abs/1907.11826 (2019) - [i42]Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm. CoRR abs/1908.10859 (2019) - [i41]Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, Peter L. Bartlett:
An Efficient Sampling Algorithm for Non-smooth Composite Potentials. CoRR abs/1910.00551 (2019) - [i40]Tan M. Nguyen, Nan Ye, Peter L. Bartlett:
Learning Near-optimal Convex Combinations of Basis Models with Generalization Guarantees. CoRR abs/1910.03742 (2019) - [i39]Peter L. Bartlett, Jonathan Baxter:
Hebbian Synaptic Modifications in Spiking Neurons that Learn. CoRR abs/1911.07247 (2019) - [i38]Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing. CoRR abs/1912.05153 (2019) - 2018
- [c103]Xiang Cheng, Fred (Farbod) Roosta, Stefan Palombo, Peter L. Bartlett, Michael W. Mahoney:
FLAG n' FLARE: Fast Linearly-Coupled Adaptive Gradient Methods. AISTATS 2018: 404-414 - [c102]Dong Yin, Ashwin Pananjady, Maximilian Lam, Dimitris S. Papailiopoulos, Kannan Ramchandran, Peter L. Bartlett:
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning. AISTATS 2018: 1998-2007 - [c101]Xiang Cheng, Peter L. Bartlett:
Convergence of Langevin MCMC in KL-divergence. ALT 2018: 186-211 - [c100]Xiang Cheng, Niladri S. Chatterji, Peter L. Bartlett, Michael I. Jordan:
Underdamped Langevin MCMC: A non-asymptotic analysis. COLT 2018: 300-323 - [c99]Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko:
Best of both worlds: Stochastic & adversarial best-arm identification. COLT 2018: 918-949 - [c98]Martin Péron, Peter L. Bartlett, Kai Helge Becker, Kate J. Helmstedt
, Iadine Chadès:
Two Approximate Dynamic Programming Algorithms for Managing Complete SIS Networks. COMPASS 2018: 8:1-8:10 - [c97]Peter L. Bartlett, David P. Helmbold, Philip M. Long:
Gradient descent with identity initialization efficiently learns positive definite linear transformations. ICML 2018: 520-529 - [c96]Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan:
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo. ICML 2018: 763-772 - [c95]Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett:
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. ICML 2018: 5636-5645 - [c94]Alan Malek, Peter L. Bartlett:
Horizon-Independent Minimax Linear Regression. NeurIPS 2018: 5264-5273 - [c93]Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan:
Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation. NeurIPS 2018: 7016-7025 - [i37]Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan:
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo. CoRR abs/1802.05431 (2018) - [i36]Peter L. Bartlett, David P. Helmbold, Philip M. Long:
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. CoRR abs/1802.06093 (2018) - [i35]Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett:
Online learning with kernel losses. CoRR abs/1802.09732 (2018) - [i34]Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett:
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. CoRR abs/1803.01498 (2018) - [i33]Peter L. Bartlett, Steven N. Evans, Philip M. Long:
Representing smooth functions as compositions of near-identity functions with implications for deep network optimization. CoRR abs/1804.05012 (2018) - [i32]Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett, Michael I. Jordan:
Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting. CoRR abs/1805.01648 (2018) - [i31]Vidya Muthukumar, Mitas Ray, Anant Sahai, Peter L. Bartlett:
Best of many worlds: Robust model selection for online supervised learning. CoRR abs/1805.08562 (2018) - [i30]Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett:
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning. CoRR abs/1806.05358 (2018) - [i29]Peter L. Bartlett, Victor Gabillon, Michal Valko:
A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. CoRR abs/1810.00997 (2018) - [i28]Dong Yin, Kannan Ramchandran, Peter L. Bartlett:
Rademacher Complexity for Adversarially Robust Generalization. CoRR abs/1810.11914 (2018) - [i27]Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan:
Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation. CoRR abs/1811.08393 (2018) - [i26]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. CoRR abs/1812.08305 (2018) - 2017
- [j48]Fares Hedayati, Peter L. Bartlett:
Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction. IEEE Trans. Inf. Theory 63(10): 6767-6773 (2017) - [c92]Martin Péron, Kai Helge Becker, Peter L. Bartlett, Iadine Chades:
Fast-Tracking Stationary MOMDPs for Adaptive Management Problems. AAAI 2017: 4531-4537 - [c91]Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek:
Hit-and-Run for Sampling and Planning in Non-Convex Spaces. AISTATS 2017: 888-895 - [c90]Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon:
Recovery Guarantees for One-hidden-layer Neural Networks. ICML 2017: 4140-4149 - [c89]Niladri S. Chatterji, Peter L. Bartlett:
Alternating minimization for dictionary learning with random initialization. NIPS 2017: 1997-2006 - [c88]Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon:
Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem. NIPS 2017: 3033-3042 - [c87]Peter L. Bartlett, Dylan J. Foster, Matus Telgarsky:
Spectrally-normalized margin bounds for neural networks. NIPS 2017: 6240-6249 - [c86]Walid Krichene, Peter L. Bartlett:
Acceleration and Averaging in Stochastic Descent Dynamics. NIPS 2017: 6796-6806 - [i25]Nan Ye, Peter L. Bartlett:
Approximate and Stochastic Greedy Optimization. CoRR abs/1705.09396 (2017) - [i24]Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon:
Recovery Guarantees for One-hidden-layer Neural Networks. CoRR abs/1706.03175 (2017) - [i23]