| 2009 |
|---|
| 79 | EE | Jacob Abernethy,
Alekh Agarwal,
Peter L. Bartlett,
Alexander Rakhlin:
A Stochastic View of Optimal Regret through Minimax Duality
CoRR abs/0903.5328: (2009) |
| 78 | EE | Benjamin I. P. Rubinstein,
Peter L. Bartlett,
J. Hyam Rubinstein:
Shifting: One-inclusion mistake bounds and sample compression.
J. Comput. Syst. Sci. 75(1): 37-59 (2009) |
| 2008 |
|---|
| 77 | EE | Marco Barreno,
Peter L. Bartlett,
Fuching Jack Chi,
Anthony D. Joseph,
Blaine Nelson,
Benjamin I. P. Rubinstein,
Udam Saini,
J. Doug Tygar:
Open problems in the security of learning.
AISec 2008: 19-26 |
| 76 | EE | Peter L. Bartlett,
Varsha Dani,
Thomas P. Hayes,
Sham Kakade,
Alexander Rakhlin,
Ambuj Tewari:
High-Probability Regret Bounds for Bandit Online Linear Optimization.
COLT 2008: 335-342 |
| 75 | EE | Jacob Abernethy,
Peter L. Bartlett,
Alexander Rakhlin,
Ambuj Tewari:
Optimal Stragies and Minimax Lower Bounds for Online Convex Games.
COLT 2008: 415-424 |
| 74 | EE | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
Correction to "The Importance of Convexity in Learning With Squared Loss".
IEEE Transactions on Information Theory 54(9): 4395 (2008) |
| 2007 |
|---|
| 73 | EE | Ambuj Tewari,
Peter L. Bartlett:
Bounded Parameter Markov Decision Processes with Average Reward Criterion.
COLT 2007: 263-277 |
| 72 | EE | Jacob Abernethy,
Peter L. Bartlett,
Alexander Rakhlin:
Multitask Learning with Expert Advice.
COLT 2007: 484-498 |
| 71 | EE | Alexander Rakhlin,
Jacob Abernethy,
Peter L. Bartlett:
Online discovery of similarity mappings.
ICML 2007: 767-774 |
| 70 | EE | Peter L. Bartlett,
Elad Hazan,
Alexander Rakhlin:
Adaptive Online Gradient Descent.
NIPS 2007 |
| 69 | EE | Ambuj Tewari,
Peter L. Bartlett:
Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs.
NIPS 2007 |
| 2006 |
|---|
| 68 | EE | Peter L. Bartlett,
Mikhail Traskin:
AdaBoost is Consistent.
NIPS 2006: 105-112 |
| 67 | EE | Benjamin I. P. Rubinstein,
Peter L. Bartlett,
J. Hyam Rubinstein:
Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds.
NIPS 2006: 1193-1200 |
| 66 | EE | Peter L. Bartlett,
Ambuj Tewari:
Sample Complexity of Policy Search with Known Dynamics.
NIPS 2006: 97-104 |
| 2005 |
|---|
| 65 | EE | Ambuj Tewari,
Peter L. Bartlett:
On the Consistency of Multiclass Classification Methods.
COLT 2005: 143-157 |
| 2004 |
|---|
| 64 | EE | Peter L. Bartlett,
Shahar Mendelson,
Petra Philips:
Local Complexities for Empirical Risk Minimization.
COLT 2004: 270-284 |
| 63 | EE | Peter L. Bartlett,
Ambuj Tewari:
Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results.
COLT 2004: 564-578 |
| 62 | EE | Peter L. Bartlett,
Michael Collins,
Benjamin Taskar,
David A. McAllester:
Exponentiated Gradient Algorithms for Large-margin Structured Classification.
NIPS 2004 |
| 61 | EE | Evan Greensmith,
Peter L. Bartlett,
Jonathan Baxter:
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.
Journal of Machine Learning Research 5: 1471-1530 (2004) |
| 60 | EE | Gert R. G. Lanckriet,
Nello Cristianini,
Peter L. Bartlett,
Laurent El Ghaoui,
Michael I. Jordan:
Learning the Kernel Matrix with Semidefinite Programming.
Journal of Machine Learning Research 5: 27-72 (2004) |
| 2003 |
|---|
| 59 | EE | Peter L. Bartlett,
Michael I. Jordan,
Jon D. McAuliffe:
Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates.
NIPS 2003 |
| 2002 |
|---|
| 58 | EE | Peter L. Bartlett,
Olivier Bousquet,
Shahar Mendelson:
Localized Rademacher Complexities.
COLT 2002: 44-58 |
| 57 | | Gert R. G. Lanckriet,
Nello Cristianini,
Peter L. Bartlett,
Laurent El Ghaoui,
Michael I. Jordan:
Learning the Kernel Matrix with Semi-Definite Programming.
ICML 2002: 323-330 |
| 56 | EE | Peter L. Bartlett:
An Introduction to Reinforcement Learning Theory: Value Function Methods.
Machine Learning Summer School 2002: 184-202 |
| 55 | | Ying Guo,
Peter L. Bartlett,
John Shawe-Taylor,
Robert C. Williamson:
Covering numbers for support vector machines.
IEEE Transactions on Information Theory 48(1): 239-250 (2002) |
| 54 | EE | Peter L. Bartlett,
Paul Fischer,
Klaus-Uwe Höffgen:
Exploiting Random Walks for Learning.
Inf. Comput. 176(2): 121-135 (2002) |
| 53 | EE | Peter L. Bartlett,
Jonathan Baxter:
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning.
J. Comput. Syst. Sci. 64(1): 133-150 (2002) |
| 52 | EE | Llew Mason,
Peter L. Bartlett,
Mostefa Golea:
Generalization Error of Combined Classifiers.
J. Comput. Syst. Sci. 65(2): 415-438 (2002) |
| 51 | EE | Peter L. Bartlett,
Shahar Mendelson:
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results.
Journal of Machine Learning Research 3: 463-482 (2002) |
| 50 | | Peter L. Bartlett,
Stéphane Boucheron,
Gábor Lugosi:
Model Selection and Error Estimation.
Machine Learning 48(1-3): 85-113 (2002) |
| 49 | EE | Peter L. Bartlett,
Shai Ben-David:
Hardness results for neural network approximation problems.
Theor. Comput. Sci. 284(1): 53-66 (2002) |
| 2001 |
|---|
| 48 | EE | Peter L. Bartlett,
Shahar Mendelson:
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results.
COLT/EuroCOLT 2001: 224-240 |
| 47 | EE | Evan Greensmith,
Peter L. Bartlett,
Jonathan Baxter:
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.
NIPS 2001: 1507-1514 |
| 46 | EE | Jonathan Baxter,
Peter L. Bartlett:
Infinite-Horizon Policy-Gradient Estimation.
J. Artif. Intell. Res. (JAIR) 15: 319-350 (2001) |
| 45 | EE | Jonathan Baxter,
Peter L. Bartlett,
Lex Weaver:
Experiments with Infinite-Horizon, Policy-Gradient Estimation.
J. Artif. Intell. Res. (JAIR) 15: 351-381 (2001) |
| 2000 |
|---|
| 44 | | Peter L. Bartlett,
Jonathan Baxter:
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning.
COLT 2000: 133-141 |
| 43 | | Peter L. Bartlett,
Stéphane Boucheron,
Gábor Lugosi:
Model Selection and Error Estimation.
COLT 2000: 286-297 |
| 42 | | Jonathan Baxter,
Peter L. Bartlett:
Reinforcement Learning in POMDP's via Direct Gradient Ascent.
ICML 2000: 41-48 |
| 41 | | Alex J. Smola,
Peter L. Bartlett:
Sparse Greedy Gaussian Process Regression.
NIPS 2000: 619-625 |
| 40 | | Martin Anthony,
Peter L. Bartlett:
Function Learning From Interpolation.
Combinatorics, Probability & Computing 9(3): (2000) |
| 39 | | Llew Mason,
Peter L. Bartlett,
Jonathan Baxter:
Improved Generalization Through Explicit Optimization of Margins.
Machine Learning 38(3): 243-255 (2000) |
| 38 | | Peter L. Bartlett,
Shai Ben-David,
Sanjeev R. Kulkarni:
Learning Changing Concepts by Exploiting the Structure of Change.
Machine Learning 41(2): 153-174 (2000) |
| 37 | | Bernhard Schölkopf,
Alex J. Smola,
Robert C. Williamson,
Peter L. Bartlett:
New Support Vector Algorithms.
Neural Computation 12(5): 1207-1245 (2000) |
| 1999 |
|---|
| 36 | EE | Ying Guo,
Peter L. Bartlett,
John Shawe-Taylor,
Robert C. Williamson:
Covering Numbers for Support Vector Machines.
COLT 1999: 267-277 |
| 35 | EE | Peter L. Bartlett,
Shai Ben-David:
Hardness Results for Neural Network Approximation Problems.
EuroCOLT 1999: 50-62 |
| 34 | EE | Llew Mason,
Jonathan Baxter,
Peter L. Bartlett,
Marcus R. Frean:
Boosting Algorithms as Gradient Descent.
NIPS 1999: 512-518 |
| 1998 |
|---|
| 33 | EE | Peter L. Bartlett,
Vitaly Maiorov,
Ron Meir:
Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks.
NIPS 1998: 190-196 |
| 32 | EE | Llew Mason,
Peter L. Bartlett,
Jonathan Baxter:
Direct Optimization of Margins Improves Generalization in Combined Classifiers.
NIPS 1998: 288-294 |
| 31 | EE | Bernhard Schölkopf,
Peter L. Bartlett,
Alex J. Smola,
Robert C. Williamson:
Shrinking the Tube: A New Support Vector Regression Algorithm.
NIPS 1998: 330-336 |
| 30 | | Peter L. Bartlett:
The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network.
IEEE Transactions on Information Theory 44(2): 525-536 (1998) |
| 29 | | Peter L. Bartlett,
Tamás Linder,
Gábor Lugosi:
The Minimax Distortion Redundancy in Empirical Quantizer Design.
IEEE Transactions on Information Theory 44(5): 1802-1813 (1998) |
| 28 | | John Shawe-Taylor,
Peter L. Bartlett,
Robert C. Williamson,
Martin Anthony:
Structural Risk Minimization Over Data-Dependent Hierarchies.
IEEE Transactions on Information Theory 44(5): 1926-1940 (1998) |
| 27 | | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
The Importance of Convexity in Learning with Squared Loss.
IEEE Transactions on Information Theory 44(5): 1974-1980 (1998) |
| 26 | | Peter L. Bartlett,
Philip M. Long:
Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions.
J. Comput. Syst. Sci. 56(2): 174-190 (1998) |
| 25 | | Peter L. Bartlett,
Vitaly Maiorov,
Ron Meir:
Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks.
Neural Computation 10(8): 2159-2173 (1998) |
| 1997 |
|---|
| 24 | | Peter L. Bartlett,
Tamás Linder,
Gábor Lugosi:
A Minimax Lower Bound for Empirical Quantizer Design.
EuroCOLT 1997: 210-222 |
| 23 | | Jonathan Baxter,
Peter L. Bartlett:
A Result Relating Convex n-Widths to Covering Numbers with some Applications to Neural Networks.
EuroCOLT 1997: 251-259 |
| 22 | | Mostefa Golea,
Peter L. Bartlett,
Wee Sun Lee,
Llew Mason:
Generalization in Decision Trees and DNF: Does Size Matter?
NIPS 1997 |
| 21 | | Jonathan Baxter,
Peter L. Bartlett:
The Canonical Distortion Measure in Feature Space and 1-NN Classification.
NIPS 1997 |
| 20 | | Peter L. Bartlett,
Sanjeev R. Kulkarni,
S. E. Posner:
Covering numbers for real-valued function classes.
IEEE Transactions on Information Theory 43(5): 1721-1724 (1997) |
| 19 | EE | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes'.
Neural Computation 9(4): 765-769 (1997) |
| 1996 |
|---|
| 18 | EE | Peter L. Bartlett,
Shai Ben-David,
Sanjeev R. Kulkarni:
Learning Changing Concepts by Exploiting the Structure of Change.
COLT 1996: 131-139 |
| 17 | EE | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
The Importance of Convexity in Learning with Squared Loss.
COLT 1996: 140-146 |
| 16 | EE | John Shawe-Taylor,
Peter L. Bartlett,
Robert C. Williamson,
Martin Anthony:
A Framework for Structural Risk Minimisation.
COLT 1996: 68-76 |
| 15 | EE | Peter L. Bartlett:
For Valid Generalization the Size of the Weights is More Important than the Size of the Network.
NIPS 1996: 134-140 |
| 14 | | Martin Anthony,
Peter L. Bartlett,
Yuval Ishai,
John Shawe-Taylor:
Valid Generalisation from Approximate Interpolation.
Combinatorics, Probability & Computing 5: 191-214 (1996) |
| 13 | | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
Efficient agnostic learning of neural networks with bounded fan-in.
IEEE Transactions on Information Theory 42(6): 2118-2132 (1996) |
| 12 | | Peter L. Bartlett,
Philip M. Long,
Robert C. Williamson:
Fat-Shattering and the Learnability of Real-Valued Functions.
J. Comput. Syst. Sci. 52(3): 434-452 (1996) |
| 1995 |
|---|
| 11 | EE | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
On Efficient Agnostic Learning of Linear Combinations of Basis Functions.
COLT 1995: 369-376 |
| 10 | EE | Peter L. Bartlett,
Philip M. Long:
More Theorems about Scale-sensitive Dimensions and Learning.
COLT 1995: 392-401 |
| 9 | | Martin Anthony,
Peter L. Bartlett:
Function learning from interpolation.
EuroCOLT 1995: 211-221 |
| 8 | EE | Adam Kowalczyk,
Jacek Szymanski,
Peter L. Bartlett,
Robert C. Williamson:
Examples of learning curves from a modified VC-formalism.
NIPS 1995: 344-350 |
| 1994 |
|---|
| 7 | EE | Peter L. Bartlett,
Philip M. Long,
Robert C. Williamson:
Fat-Shattering and the Learnability of Real-Valued Functions.
COLT 1994: 299-310 |
| 6 | EE | Peter L. Bartlett,
Paul Fischer,
Klaus-Uwe Höffgen:
Exploiting Random Walks for Learning.
COLT 1994: 318-327 |
| 5 | EE | Wee Sun Lee,
Peter L. Bartlett,
Robert C. Williamson:
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes.
COLT 1994: 362-367 |
| 1993 |
|---|
| 4 | EE | Peter L. Bartlett:
Lower Bounds on the Vapnik-Chervonenkis Dimension of Multi-Layer Threshold Networks.
COLT 1993: 144-150 |
| 1992 |
|---|
| 3 | EE | Peter L. Bartlett:
Learning With a Slowly Changing Distribution.
COLT 1992: 243-252 |
| 1991 |
|---|
| 2 | EE | Peter L. Bartlett,
Robert C. Williamson:
Investigating the Distribution Assumptions in the Pac Learning Model.
COLT 1991: 24-32 |
| 1 | EE | Robert C. Williamson,
Peter L. Bartlett:
Splines, Rational Functions and Neural Networks.
NIPS 1991: 1040-1047 |
