COLT 2010 - PDF Preprint Papers

COLT 2010 Annual Workshop on Computational Learning Theory

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed COLT-2010 Paper

click to vote

COLT
2010
Springer

238views Machine Learning» more COLT 2010»

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

13 years 2 months ago

Download www.colt2010.org

We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...

John Duchi, Elad Hazan, Yoram Singer

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	238	Adaptive Subgradient Methods for Online Learning and Stochastic Optimization	claim
2	217	Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback	claim
3	207	An Asymptotically Optimal Bandit Algorithm for Bounded Support Models	claim
4	205	Convex Games in Banach Spaces	claim
5	201	Forest Density Estimation	claim
6	193	Hedging Structured Concepts	claim
7	191	Best Arm Identification in Multi-Armed Bandits	claim
8	186	The Convergence Rate of AdaBoost	claim
9	186	Following the Flattened Leader	claim
10	183	Regret Minimization With Concept Drift	claim
11	182	Principal Component Analysis with Contaminated Data: The High Dimensional Case	claim
12	181	Composite Objective Mirror Descent	claim
13	177	Robust Selective Sampling from Single and Multiple Teachers	claim
14	169	Learning Rotations with Little Regret	claim
15	167	Active Learning on Trees and Graphs	claim
16	166	Deterministic Sparse Fourier Approximation via Fooling Arithmetic Progressions	claim
17	165	Mansour's Conjecture is True for Random DNF Formulas	claim
18	161	Quantum Predictive Learning and Communication Complexity with Single Input	claim
19	160	On-line Variance Minimization in O(n2) per Trial?	claim
20	157	Efficient Classification for Metric Data	claim
21	156	Characterization of Linkage-based Clustering	claim
22	150	Sparse Recovery in Convex Hulls of Infinite Dictionaries	claim
23	150	Toward Learning Gaussian Mixtures with Arbitrary Separation	claim
24	150	Robust Hierarchical Clustering	claim
25	149	Open Loop Optimistic Planning	claim
26	140	Open Problem: Analyzing Ant Robot Coverage	claim
27	138	Ranking with Kernels in Fourier space	claim
28	137	Voting Paradoxes	claim
29	136	Improved Guarantees for Agnostic Learning of Disjunctions	claim
30	129	Nonparametric Bandits with Covariates	claim
31	128	Theoretical Justification of Popular Link Prediction Heuristics	claim
32	126	The Online Loop-free Stochastic Shortest-Path Problem	claim
33	122	Inferring Descriptive Generalisations of Formal Languages	claim
34	120	Learning to Create is as Hard as Learning to Appreciate	claim
35	117	Strongly Non-U-Shaped Learning Results by General Techniques	claim
36	117	Learning with Global Cost in Stochastic Environments	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers