| 1 |
Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition
Rong Ge, Furong Huang, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
1.1K |
11 years ago |
| 2 |
The Power of Depth for Feedforward Neural Networks
Ronen Eldan, Ohad Shamir
|
👻
Ghosted
|
cs.LG
|
777 |
10 years ago |
| 3 |
Benefits of depth in neural networks
Matus Telgarsky
|
👻
Ghosted
|
cs.LG
|
671 |
10 years ago |
| 4 |
Norm-Based Capacity Control in Neural Networks
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro
|
👻
Ghosted
|
cs.LG
|
642 |
11 years ago |
| 5 |
Size-Independent Sample Complexity of Neural Networks
Noah Golowich, Alexander Rakhlin, Ohad Shamir
|
👻
Ghosted
|
cs.LG
|
602 |
8 years ago |
| 6 |
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky
|
👻
Ghosted
|
cs.LG
|
561 |
9 years ago |
| 7 |
On the Expressive Power of Deep Learning: A Tensor Analysis
Nadav Cohen, Or Sharir, Amnon Shashua
|
👻
Ghosted
|
cs.NE
|
481 |
10 years ago |
| 8 |
Learning Internal Representations (COLT 1995)
Jonathan Baxter
|
👻
Ghosted
|
cs.LG
|
406 |
6 years ago |
| 9 |
Optimal Best Arm Identification with Fixed Confidence
Aurélien Garivier, Emilie Kaufmann
|
👻
Ghosted
|
math.ST
|
384 |
10 years ago |
| 10 |
Optimal approximation of continuous functions by very deep ReLU networks
Dmitry Yarotsky
|
👻
Ghosted
|
cs.NE
|
324 |
8 years ago |
| 11 |
Underdamped Langevin MCMC: A non-asymptotic analysis
Xiang Cheng, Niladri S. Chatterji, ... (+2 more)
|
👻
Ghosted
|
stat.ML
|
322 |
8 years ago |
| 12 |
First-order Methods for Geodesically Convex Optimization
Hongyi Zhang, Suvrit Sra
|
👻
Ghosted
|
math.OC
|
319 |
10 years ago |
| 13 |
Simple Bayesian Algorithms for Best Arm Identification
Daniel Russo
|
👻
Ghosted
|
cs.LG
|
304 |
10 years ago |
| 14 |
Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
Chi Jin, Praneeth Netrapalli, Michael I. Jordan
|
👻
Ghosted
|
cs.LG
|
285 |
8 years ago |
| 15 |
A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics
Yuchen Zhang, Percy Liang, Moses Charikar
|
👻
Ghosted
|
cs.LG
|
244 |
9 years ago |
| 16 |
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
Dongruo Zhou, Quanquan Gu, Csaba Szepesvari
|
👻
Ghosted
|
cs.LG
|
228 |
5 years ago |
| 17 |
Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem
Andre Wibisono
|
👻
Ghosted
|
math.OC
|
201 |
8 years ago |
| 18 |
Simple, Efficient, and Neural Algorithms for Sparse Coding
Sanjeev Arora, Rong Ge, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
200 |
11 years ago |
| 19 |
Reasoning About Generalization via Conditional Mutual Information
Thomas Steinke, Lydia Zakynthinou
|
👻
Ghosted
|
cs.LG
|
192 |
6 years ago |
| 20 |
Stochastic Block Model and Community Detection in the Sparse Graphs: A spectral algorithm with optimal rate of recovery
Peter Chin, Anup Rao, Van Vu
|
👻
Ghosted
|
cs.DS
|
180 |
11 years ago |
| 21 |
Dropping Convexity for Faster Semi-definite Optimization
Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
|
👻
Ghosted
|
stat.ML
|
178 |
10 years ago |
| 22 |
Tensor principal component analysis via sum-of-squares proofs
Samuel B. Hopkins, Jonathan Shi, David Steurer
|
👻
Ghosted
|
cs.LG
|
174 |
10 years ago |
| 23 |
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints
Wenlong Mou, Liwei Wang, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
172 |
8 years ago |
| 24 |
High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
Vitaly Feldman, Jan Vondrak
|
👻
Ghosted
|
cs.LG
|
170 |
7 years ago |
| 25 |
Online Learning with Feedback Graphs: Beyond Bandits
Noga Alon, Nicolò Cesa-Bianchi, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
170 |
11 years ago |
| 26 |
Corralling a Band of Bandit Algorithms
Alekh Agarwal, Haipeng Luo, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
168 |
9 years ago |
| 27 |
Privately Learning High-Dimensional Distributions
Gautam Kamath, Jerry Li, ... (+2 more)
|
👻
Ghosted
|
cs.DS
|
165 |
7 years ago |
| 28 |
Efficient Algorithms for Outlier-Robust Regression
Adam Klivans, Pravesh K. Kothari, Raghu Meka
|
👻
Ghosted
|
cs.LG
|
163 |
8 years ago |
| 29 |
Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem
Alexandra Carpentier, Andrea Locatelli
|
👻
Ghosted
|
stat.ML
|
163 |
9 years ago |
| 30 |
Tight Analyses for Non-Smooth Stochastic Gradient Descent
Nicholas J. A. Harvey, Christopher Liaw, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
158 |
7 years ago |
| 31 |
Delay and Cooperation in Nonstochastic Bandits
Nicolo' Cesa-Bianchi, Claudio Gentile, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
156 |
10 years ago |
| 32 |
The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
Stephen Tu, Benjamin Recht
|
👻
Ghosted
|
cs.LG
|
154 |
7 years ago |
| 33 |
Efficient Contextual Bandits in Non-stationary Worlds
Haipeng Luo, Chen-Yu Wei, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
148 |
8 years ago |
| 34 |
Contextual Dueling Bandits
Miroslav Dudík, Katja Hofmann, ... (+3 more)
|
👻
Ghosted
|
cs.LG
|
145 |
11 years ago |
| 35 |
Efficient approaches for escaping higher order saddle points in non-convex optimization
Anima Anandkumar, Rong Ge
|
👻
Ghosted
|
cs.LG
|
143 |
10 years ago |
| 36 |
Reinforcement Learning of POMDPs using Spectral Methods
Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar
|
👻
Ghosted
|
cs.AI
|
141 |
10 years ago |
| 37 |
Sharper bounds for uniformly stable algorithms
Olivier Bousquet, Yegor Klochkov, Nikita Zhivotovskiy
|
👻
Ghosted
|
cs.LG
|
136 |
6 years ago |
| 38 |
Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm
Prateek Jain, Chi Jin, ... (+3 more)
|
👻
Ghosted
|
cs.LG
|
134 |
10 years ago |
| 39 |
Fundamental Limits of Weak Recovery with Applications to Phase Retrieval
Marco Mondelli, Andrea Montanari
|
👻
Ghosted
|
stat.ML
|
133 |
8 years ago |
| 40 |
Learning Simple Auctions
Jamie Morgenstern, Tim Roughgarden
|
👻
Ghosted
|
cs.LG
|
132 |
9 years ago |
| 41 |
Monte Carlo Markov Chain Algorithms for Sampling Strongly Rayleigh Distributions and Determinantal Point Processes
Nima Anari, Shayan Oveis Gharan, Alireza Rezaei
|
👻
Ghosted
|
cs.LG
|
132 |
10 years ago |
| 42 |
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
Emmanuel Abbe, Enric Boix-Adsera, Theodor Misiakiewicz
|
👻
Ghosted
|
cs.LG
|
131 |
4 years ago |
| 43 |
Reliably Learning the ReLU in Polynomial Time
Surbhi Goel, Varun Kanade, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
128 |
9 years ago |
| 44 |
Ten Steps of EM Suffice for Mixtures of Two Gaussians
Constantinos Daskalakis, Christos Tzamos, Manolis Zampetakis
|
👻
Ghosted
|
stat.ML
|
128 |
9 years ago |
| 45 |
Information-theoretic thresholds for community detection in sparse networks
Jess Banks, Cristopher Moore
|
👻
Ghosted
|
math.PR
|
128 |
10 years ago |
| 46 |
Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
Yin Tat Lee, Zhao Song, Qiuyi Zhang
|
👻
Ghosted
|
cs.DS
|
127 |
6 years ago |
| 47 |
Reducibility and Computational Lower Bounds for Problems with Planted Sparse Structure
Matthew Brennan, Guy Bresler, Wasim Huleihel
|
🔮
The Ethereal
|
cs.CC
|
120 |
7 years ago |
| 48 |
Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
Jonathan Scarlett, Ilijia Bogunovic, Volkan Cevher
|
👻
Ghosted
|
stat.ML
|
117 |
8 years ago |
| 49 |
An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
Peter Auer, Chao-Kai Chiang
|
👻
Ghosted
|
cs.LG
|
116 |
9 years ago |
| 50 |
Corruption-robust exploration in episodic reinforcement learning
Thodoris Lykouris, Max Simchowitz, ... (+2 more)
|
👻
Ghosted
|
cs.LG
|
112 |
6 years ago |