Peter L. Bartlett [FOAF] [Follow]

Position:	Professor
Affiliation:	Division of Computer Science and Department of Statistics UC Berkeley
Address:	University of California, Berkeley Department of Statistics 367 Evans Hall #3860 Berkeley, CA 94720-3860
Phone:	+1 510-642-8079
Fax:	+1 510-642-7892
Email:
Homepage:	http://stat-www.berkeley.edu/~bartlett/
	[Edit]

Statistics:	H-index: 28 (See all experts' h-index.) total citation number: 4667 highest-cited paper: New Support Vector Algorithms (2000) at Neural Computation (Cited By 858) More Statistics...

bio:

Peter Bartlett is a professor in the Division of Computer Science and Department of Statistics at th ... More

Research Interest:

Reinforcement Learning, Gradient-Based Reinforcement Learning, Lower Bounds, Efficient Agnostic Learning, Function Learning

Show Temporal Interests (Do you want to see the change of his/her research interests?)

Publications: [Edit disambiguation Result]

Group By Year Group By Category

2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996 1995 1994 1993 1992 1991

2009 Top (4)
[82]	Jacob Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin. A Stochastic View of Optimal Regret through Minimax Duality. CoRR, 2009. Cited By 7[Bibtex]
[81]	Benjamin I. P. Rubinstein, Peter L. Bartlett, Ling Huang, Nina Taft. Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning. CoRR, 2009. Cited By 2[Bibtex]
[80]	Adam Barth, Benjamin I. P. Rubinstein, Mukund Sundararajan, John C. Mitchell, Dawn Xiaodong Song, Peter L. Bartlett. A Learning-Based Approach to Reactive Security. CoRR, 2009. Cited By 1[Bibtex]
[79]	Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein. Shifting: One-inclusion mistake bounds and sample compression. J. Comput. Syst. Sci., 2009: 37~59 Cited By 9[Bibtex]
2008 Top (4)
[78]	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. pp.19~26 Cited By 4[Bibtex]
[77]	Jacob Abernethy, Peter L. Bartlett, Alexander Rakhlin, Ambuj Tewari. Optimal Stragies and Minimax Lower Bounds for Online Convex Games. COLT'2008. pp.415~424 [Bibtex]
[76]	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. pp.335~342 Cited By 12[Bibtex]
[75]	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, 2008: 4395~4395 Cited By 65[Bibtex]
2007 Top (5)
[74]	Ambuj Tewari, Peter L. Bartlett. Bounded Parameter Markov Decision Processes with Average Reward Criterion. COLT'2007. pp.263~277 Cited By 5[Bibtex]
[73]	Jacob Abernethy, Peter L. Bartlett, Alexander Rakhlin. Multitask Learning with Expert Advice. COLT'2007. pp.484~498 [Bibtex]
[72]	Alexander Rakhlin, Jacob Abernethy, Peter L. Bartlett. Online discovery of similarity mappings. ICML'2007. pp.767~774 [Bibtex]
[71]	Ambuj Tewari, Peter L. Bartlett. Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs. NIPS'2007. Cited By 15[Bibtex]
[70]	Peter L. Bartlett, Elad Hazan, Alexander Rakhlin. Adaptive Online Gradient Descent. NIPS'2007. Cited By 19[Bibtex]
2006 Top (3)
[69]	Peter L. Bartlett, Ambuj Tewari. Sample Complexity of Policy Search with Known Dynamics. NIPS'2006. pp.97~104 Cited By 2[Bibtex]
[68]	Peter L. Bartlett, Mikhail Traskin. AdaBoost is Consistent. NIPS'2006. pp.105~112 Cited By 20[Bibtex]
[67]	Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein. Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds. NIPS'2006. pp.1193~1200 Cited By 5[Bibtex]
2005 Top (1)
[66]	Ambuj Tewari, Peter L. Bartlett. On the Consistency of Multiclass Classification Methods. COLT'2005. pp.143~157 Cited By 48[Bibtex]
2004 Top (5)
[65]	Peter L. Bartlett, Shahar Mendelson, Petra Philips. Local Complexities for Empirical Risk Minimization. COLT'2004. pp.270~284 Cited By 8[Bibtex]
[64]	Peter L. Bartlett, Ambuj Tewari. Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results. COLT'2004. pp.564~578 Cited By 44[Bibtex]
[63]	Peter L. Bartlett, Michael Collins, Benjamin Taskar, David A. McAllester. Exponentiated Gradient Algorithms for Large-margin Structured Classification. NIPS'2004. [Bibtex] [PDF]
[62]	Evan Greensmith, Peter L. Bartlett, Jonathan Baxter. Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. Journal of Machine Learning Research, 2004: 1471~1530 Cited By 53[Bibtex] [PDF]
[61]	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, 2004: 27~72 Cited By 775[Bibtex]
2003 Top (1)
[60]	Peter L. Bartlett, Michael I. Jordan, Jon D. McAuliffe. Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates. NIPS'2003. Cited By 18[Bibtex] [PDF]
2002 Top (10)
[59]	Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson. Localized Rademacher Complexities. COLT'2002. pp.44~58 Cited By 141[Bibtex]
[58]	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. pp.323~330 Cited By 775[Bibtex] [PDF]
[57]	Peter L. Bartlett. An Introduction to Reinforcement Learning Theory: Value Function Methods. Machine Learning Summer School'2002. pp.184~202 [Bibtex]
[56]	Peter L. Bartlett, Paul Fischer, Klaus-Uwe Hoffgen. Exploiting Random Walks for Learning. Inf. Comput., 2002: 121~135 Cited By 14[Bibtex] [PDF]
[55]	Peter L. Bartlett, Jonathan Baxter. Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. J. Comput. Syst. Sci., 2002: 133~150 Cited By 26[Bibtex] [PDF]
[54]	Llew Mason, Peter L. Bartlett, Mostefa Golea. Generalization Error of Combined Classifiers. J. Comput. Syst. Sci., 2002: 415~438 Cited By 6[Bibtex] [PDF]
[53]	Peter L. Bartlett, Shahar Mendelson. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. Journal of Machine Learning Research, 2002: 463~482 Cited By 279[Bibtex] [PDF]
[52]	Peter L. Bartlett, Stephane Boucheron, Gabor Lugosi. Model Selection and Error Estimation. Machine Learning, 2002: 85~113 Cited By 159[Bibtex] [PDF]
[51]	Peter L. Bartlett, Shai Ben-David. Hardness results for neural network approximation problems. Theor. Comput. Sci., 2002: 53~66 [Bibtex] [PDF]
[50]	Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson. Covering numbers for support vector machines. IEEE Transactions on Information Theory, 2002: 239~250 Cited By 41[Bibtex]
2001 Top (4)
[49]	Peter L. Bartlett, Shahar Mendelson. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. COLT/EuroCOLT'2001. pp.224~240 Cited By 279[Bibtex] [PDF]
[48]	Evan Greensmith, Peter L. Bartlett, Jonathan Baxter. Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. NIPS'2001. pp.1507~1514 Cited By 53[Bibtex] [PDF]
[47]	Jonathan Baxter, Peter L. Bartlett. Infinite-Horizon Policy-Gradient Estimation. J. Artif. Intell. Res. (JAIR), 2001: 319~350 Cited By 238[Bibtex]
[46]	Jonathan Baxter, Peter L. Bartlett, Lex Weaver. Experiments with Infinite-Horizon, Policy-Gradient Estimation. J. Artif. Intell. Res. (JAIR), 2001: 351~381 Cited By 94[Bibtex]
2000 Top (8)
[45]	Peter L. Bartlett, Jonathan Baxter. Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. COLT'2000. pp.133~141 Cited By 26[Bibtex] [PDF]
[44]	Peter L. Bartlett, Stephane Boucheron, Gabor Lugosi. Model Selection and Error Estimation. COLT'2000. pp.286~297 Cited By 159[Bibtex] [PDF]
[43]	Jonathan Baxter, Peter L. Bartlett. Reinforcement Learning in POMDP's via Direct Gradient Ascent. ICML'2000. pp.41~48 Cited By 79[Bibtex]
[42]	Alex J. Smola, Peter L. Bartlett. Sparse Greedy Gaussian Process Regression. NIPS'2000. pp.619~625 Cited By 131[Bibtex] [PDF]
[41]	Martin Anthony, Peter L. Bartlett. Function Learning From Interpolation. Combinatorics, Probability Computing, 2000. Cited By 41[Bibtex]
[40]	Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni. Learning Changing Concepts by Exploiting the Structure of Change. Machine Learning, 2000: 153~174 Cited By 42[Bibtex] [PDF]
[39]	Llew Mason, Peter L. Bartlett, Jonathan Baxter. Improved Generalization Through Explicit Optimization of Margins. Machine Learning, 2000: 243~255 Cited By 91[Bibtex]
[38]	Bernhard Scholkopf, Alex J. Smola, Robert C. Williamson, Peter L. Bartlett. New Support Vector Algorithms. Neural Computation, 2000: 1207~1245 Cited By 858[Bibtex]
1999 Top (3)
[37]	Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson. Covering Numbers for Support Vector Machines. COLT'1999. pp.267~277 Cited By 41[Bibtex]
[36]	Peter L. Bartlett, Shai Ben-David. Hardness Results for Neural Network Approximation Problems. EuroCOLT'1999. pp.50~62 [Bibtex] [PDF]
[35]	Llew Mason, Jonathan Baxter, Peter L. Bartlett, Marcus R. Frean. Boosting Algorithms as Gradient Descent. NIPS'1999. pp.512~518 [Bibtex]
1998 Top (9)
[34]	Peter L. Bartlett, Vitaly Maiorov, Ron Meir. Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks. NIPS'1998. pp.190~196 Cited By 28[Bibtex] [PDF]
[33]	Llew Mason, Peter L. Bartlett, Jonathan Baxter. Direct Optimization of Margins Improves Generalization in Combined Classifiers. NIPS'1998. pp.288~294 Cited By 39[Bibtex] [PDF]
[32]	Bernhard Scholkopf, Peter L. Bartlett, Alex J. Smola, Robert C. Williamson. Shrinking the Tube: A New Support Vector Regression Algorithm. NIPS'1998. pp.330~336 [Bibtex] [PDF]
[31]	Peter L. Bartlett, Philip M. Long. Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions. J. Comput. Syst. Sci., 1998: 174~190 Cited By 29[Bibtex]
[30]	Peter L. Bartlett, Vitaly Maiorov, Ron Meir. Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks. Neural Computation, 1998: 2159~2173 Cited By 28[Bibtex] [PDF]
[29]	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, 1998: 525~536 Cited By 391[Bibtex]
[28]	Peter L. Bartlett, Tamas Linder, Gabor Lugosi. The Minimax Distortion Redundancy in Empirical Quantizer Design. IEEE Transactions on Information Theory, 1998: 1802~1813 Cited By 31[Bibtex] [PDF]
[27]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. The Importance of Convexity in Learning with Squared Loss. IEEE Transactions on Information Theory, 1998: 1974~1980 Cited By 65[Bibtex] [PDF]
[26]	John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony. Structural Risk Minimization Over Data-Dependent Hierarchies. IEEE Transactions on Information Theory, 1998: 1926~1940 Cited By 362[Bibtex] [PDF]
1997 Top (6)
[25]	Peter L. Bartlett, Tamas Linder, Gabor Lugosi. A Minimax Lower Bound for Empirical Quantizer Design. EuroCOLT'1997. pp.210~222 [Bibtex] [PDF]
[24]	Jonathan Baxter, Peter L. Bartlett. A Result Relating Convex n-Widths to Covering Numbers with some Applications to Neural Networks. EuroCOLT'1997. pp.251~259 Cited By 1[Bibtex]
[23]	Jonathan Baxter, Peter L. Bartlett. The Canonical Distortion Measure in Feature Space and 1-NN Classification. NIPS'1997. Cited By 9[Bibtex]
[22]	Mostefa Golea, Peter L. Bartlett, Wee Sun Lee, Llew Mason. Generalization in Decision Trees and DNF: Does Size Matter?. NIPS'1997. Cited By 27[Bibtex] [PDF]
[21]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes. Neural Computation, 1997: 765~769 [Bibtex]
[20]	Peter L. Bartlett, Sanjeev R. Kulkarni, S. E. Posner. Covering numbers for real-valued function classes. IEEE Transactions on Information Theory, 1997: 1721~1724 Cited By 24[Bibtex]
1996 Top (7)
[19]	Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni. Learning Changing Concepts by Exploiting the Structure of Change. COLT'1996. pp.131~139 Cited By 42[Bibtex] [PDF]
[18]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. The Importance of Convexity in Learning with Squared Loss. COLT'1996. pp.140~146 Cited By 65[Bibtex] [PDF]
[17]	John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony. A Framework for Structural Risk Minimisation. COLT'1996. pp.68~76 Cited By 69[Bibtex] [PDF]
[16]	Peter L. Bartlett. For Valid Generalization the Size of the Weights is More Important than the Size of the Network. NIPS'1996. pp.134~140 Cited By 107[Bibtex]
[15]	Martin Anthony, Peter L. Bartlett, Yuval Ishai, John Shawe-Taylor. Valid Generalisation from Approximate Interpolation. Combinatorics, Probability Computing, 1996: 191~214 Cited By 16[Bibtex] [PDF]
[14]	Peter L. Bartlett, Philip M. Long, Robert C. Williamson. Fat-Shattering and the Learnability of Real-Valued Functions. J. Comput. Syst. Sci., 1996: 434~452 Cited By 98[Bibtex] [PDF]
[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, 1996: 2118~2132 Cited By 123[Bibtex] [PDF]
1995 Top (4)
[12]	Peter L. Bartlett, Philip M. Long. More Theorems about Scale-sensitive Dimensions and Learning. COLT'1995. pp.392~401 Cited By 22[Bibtex] [PDF]
[11]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. On Efficient Agnostic Learning of Linear Combinations of Basis Functions. COLT'1995. pp.369~376 Cited By 19[Bibtex] [PDF]
[10]	Martin Anthony, Peter L. Bartlett. Function learning from interpolation. EuroCOLT'1995. pp.211~221 Cited By 41[Bibtex]
[9]	Adam Kowalczyk, Jacek Szymanski, Peter L. Bartlett, Robert C. Williamson. Examples of learning curves from a modified VC-formalism. NIPS'1995. pp.344~350 Cited By 1[Bibtex] [PDF]
1994 Top (3)
[8]	Peter L. Bartlett, Paul Fischer, Klaus-Uwe Hoffgen. Exploiting Random Walks for Learning. COLT'1994. pp.318~327 Cited By 14[Bibtex] [PDF]
[7]	Peter L. Bartlett, Philip M. Long, Robert C. Williamson. Fat-Shattering and the Learnability of Real-Valued Functions. COLT'1994. pp.299~310 Cited By 98[Bibtex] [PDF]
[6]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes. COLT'1994. pp.362~367 [Bibtex] [PDF]
1993 Top (2)
[5]	Peter L. Bartlett. Lower Bounds on the Vapnik-Chervonenkis Dimension of Multi-Layer Threshold Networks. COLT'1993. pp.144~150 Cited By 19[Bibtex] [PDF]
[4]	Peter L. Bartlett. Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks. Neural Computation, 1993: 371~373 Cited By 17[Bibtex]
1992 Top (1)
[3]	Peter L. Bartlett. Learning With a Slowly Changing Distribution. COLT'1992. pp.243~252 Cited By 32[Bibtex] [PDF]
1991 Top (2)
[2]	Peter L. Bartlett, Robert C. Williamson. Investigating the Distribution Assumptions in the Pac Learning Model. COLT'1991. pp.24~32 Cited By 16[Bibtex]
[1]	Robert C. Williamson, Peter L. Bartlett. Splines, Rational Functions and Neural Networks. NIPS'1991. pp.1040~1047 Cited By 1[Bibtex]

Machine Learning

Machine Learning(82)

Top

[82]	Jacob Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin. A Stochastic View of Optimal Regret through Minimax Duality. CoRR, 2009. Cited By 7[Bibtex]
[81]	Benjamin I. P. Rubinstein, Peter L. Bartlett, Ling Huang, Nina Taft. Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning. CoRR, 2009. Cited By 2[Bibtex]
[80]	Adam Barth, Benjamin I. P. Rubinstein, Mukund Sundararajan, John C. Mitchell, Dawn Xiaodong Song, Peter L. Bartlett. A Learning-Based Approach to Reactive Security. CoRR, 2009. Cited By 1[Bibtex]
[79]	Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein. Shifting: One-inclusion mistake bounds and sample compression. J. Comput. Syst. Sci., 2009: 37~59 Cited By 9[Bibtex]
[78]	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. pp.19~26 Cited By 4[Bibtex]
[77]	Jacob Abernethy, Peter L. Bartlett, Alexander Rakhlin, Ambuj Tewari. Optimal Stragies and Minimax Lower Bounds for Online Convex Games. COLT'2008. pp.415~424 [Bibtex]
[76]	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. pp.335~342 Cited By 12[Bibtex]
[75]	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, 2008: 4395~4395 Cited By 65[Bibtex]
[74]	Ambuj Tewari, Peter L. Bartlett. Bounded Parameter Markov Decision Processes with Average Reward Criterion. COLT'2007. pp.263~277 Cited By 5[Bibtex]
[73]	Jacob Abernethy, Peter L. Bartlett, Alexander Rakhlin. Multitask Learning with Expert Advice. COLT'2007. pp.484~498 [Bibtex]
[72]	Alexander Rakhlin, Jacob Abernethy, Peter L. Bartlett. Online discovery of similarity mappings. ICML'2007. pp.767~774 [Bibtex]
[71]	Ambuj Tewari, Peter L. Bartlett. Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs. NIPS'2007. Cited By 15[Bibtex]
[70]	Peter L. Bartlett, Elad Hazan, Alexander Rakhlin. Adaptive Online Gradient Descent. NIPS'2007. Cited By 19[Bibtex]
[69]	Peter L. Bartlett, Ambuj Tewari. Sample Complexity of Policy Search with Known Dynamics. NIPS'2006. pp.97~104 Cited By 2[Bibtex]
[68]	Peter L. Bartlett, Mikhail Traskin. AdaBoost is Consistent. NIPS'2006. pp.105~112 Cited By 20[Bibtex]
[67]	Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein. Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds. NIPS'2006. pp.1193~1200 Cited By 5[Bibtex]
[66]	Ambuj Tewari, Peter L. Bartlett. On the Consistency of Multiclass Classification Methods. COLT'2005. pp.143~157 Cited By 48[Bibtex]
[65]	Peter L. Bartlett, Shahar Mendelson, Petra Philips. Local Complexities for Empirical Risk Minimization. COLT'2004. pp.270~284 Cited By 8[Bibtex]
[64]	Peter L. Bartlett, Ambuj Tewari. Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results. COLT'2004. pp.564~578 Cited By 44[Bibtex]
[63]	Peter L. Bartlett, Michael Collins, Benjamin Taskar, David A. McAllester. Exponentiated Gradient Algorithms for Large-margin Structured Classification. NIPS'2004. [Bibtex] [PDF]
[62]	Evan Greensmith, Peter L. Bartlett, Jonathan Baxter. Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. Journal of Machine Learning Research, 2004: 1471~1530 Cited By 53[Bibtex] [PDF]
[61]	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, 2004: 27~72 Cited By 775[Bibtex]
[60]	Peter L. Bartlett, Michael I. Jordan, Jon D. McAuliffe. Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates. NIPS'2003. Cited By 18[Bibtex] [PDF]
[59]	Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson. Localized Rademacher Complexities. COLT'2002. pp.44~58 Cited By 141[Bibtex]
[58]	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. pp.323~330 Cited By 775[Bibtex] [PDF]
[57]	Peter L. Bartlett. An Introduction to Reinforcement Learning Theory: Value Function Methods. Machine Learning Summer School'2002. pp.184~202 [Bibtex]
[56]	Peter L. Bartlett, Paul Fischer, Klaus-Uwe Hoffgen. Exploiting Random Walks for Learning. Inf. Comput., 2002: 121~135 Cited By 14[Bibtex] [PDF]
[55]	Peter L. Bartlett, Jonathan Baxter. Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. J. Comput. Syst. Sci., 2002: 133~150 Cited By 26[Bibtex] [PDF]
[54]	Llew Mason, Peter L. Bartlett, Mostefa Golea. Generalization Error of Combined Classifiers. J. Comput. Syst. Sci., 2002: 415~438 Cited By 6[Bibtex] [PDF]
[53]	Peter L. Bartlett, Shahar Mendelson. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. Journal of Machine Learning Research, 2002: 463~482 Cited By 279[Bibtex] [PDF]
[52]	Peter L. Bartlett, Stephane Boucheron, Gabor Lugosi. Model Selection and Error Estimation. Machine Learning, 2002: 85~113 Cited By 159[Bibtex] [PDF]
[51]	Peter L. Bartlett, Shai Ben-David. Hardness results for neural network approximation problems. Theor. Comput. Sci., 2002: 53~66 [Bibtex] [PDF]
[50]	Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson. Covering numbers for support vector machines. IEEE Transactions on Information Theory, 2002: 239~250 Cited By 41[Bibtex]
[49]	Peter L. Bartlett, Shahar Mendelson. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. COLT/EuroCOLT'2001. pp.224~240 Cited By 279[Bibtex] [PDF]
[48]	Evan Greensmith, Peter L. Bartlett, Jonathan Baxter. Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. NIPS'2001. pp.1507~1514 Cited By 53[Bibtex] [PDF]
[47]	Jonathan Baxter, Peter L. Bartlett. Infinite-Horizon Policy-Gradient Estimation. J. Artif. Intell. Res. (JAIR), 2001: 319~350 Cited By 238[Bibtex]
[46]	Jonathan Baxter, Peter L. Bartlett, Lex Weaver. Experiments with Infinite-Horizon, Policy-Gradient Estimation. J. Artif. Intell. Res. (JAIR), 2001: 351~381 Cited By 94[Bibtex]
[45]	Peter L. Bartlett, Jonathan Baxter. Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. COLT'2000. pp.133~141 Cited By 26[Bibtex] [PDF]
[44]	Peter L. Bartlett, Stephane Boucheron, Gabor Lugosi. Model Selection and Error Estimation. COLT'2000. pp.286~297 Cited By 159[Bibtex] [PDF]
[43]	Jonathan Baxter, Peter L. Bartlett. Reinforcement Learning in POMDP's via Direct Gradient Ascent. ICML'2000. pp.41~48 Cited By 79[Bibtex]
[42]	Alex J. Smola, Peter L. Bartlett. Sparse Greedy Gaussian Process Regression. NIPS'2000. pp.619~625 Cited By 131[Bibtex] [PDF]
[41]	Martin Anthony, Peter L. Bartlett. Function Learning From Interpolation. Combinatorics, Probability Computing, 2000. Cited By 41[Bibtex]
[40]	Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni. Learning Changing Concepts by Exploiting the Structure of Change. Machine Learning, 2000: 153~174 Cited By 42[Bibtex] [PDF]
[39]	Llew Mason, Peter L. Bartlett, Jonathan Baxter. Improved Generalization Through Explicit Optimization of Margins. Machine Learning, 2000: 243~255 Cited By 91[Bibtex]
[38]	Bernhard Scholkopf, Alex J. Smola, Robert C. Williamson, Peter L. Bartlett. New Support Vector Algorithms. Neural Computation, 2000: 1207~1245 Cited By 858[Bibtex]
[37]	Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson. Covering Numbers for Support Vector Machines. COLT'1999. pp.267~277 Cited By 41[Bibtex]
[36]	Peter L. Bartlett, Shai Ben-David. Hardness Results for Neural Network Approximation Problems. EuroCOLT'1999. pp.50~62 [Bibtex] [PDF]
[35]	Llew Mason, Jonathan Baxter, Peter L. Bartlett, Marcus R. Frean. Boosting Algorithms as Gradient Descent. NIPS'1999. pp.512~518 [Bibtex]
[34]	Peter L. Bartlett, Vitaly Maiorov, Ron Meir. Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks. NIPS'1998. pp.190~196 Cited By 28[Bibtex] [PDF]
[33]	Llew Mason, Peter L. Bartlett, Jonathan Baxter. Direct Optimization of Margins Improves Generalization in Combined Classifiers. NIPS'1998. pp.288~294 Cited By 39[Bibtex] [PDF]
[32]	Bernhard Scholkopf, Peter L. Bartlett, Alex J. Smola, Robert C. Williamson. Shrinking the Tube: A New Support Vector Regression Algorithm. NIPS'1998. pp.330~336 [Bibtex] [PDF]
[31]	Peter L. Bartlett, Philip M. Long. Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions. J. Comput. Syst. Sci., 1998: 174~190 Cited By 29[Bibtex]
[30]	Peter L. Bartlett, Vitaly Maiorov, Ron Meir. Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks. Neural Computation, 1998: 2159~2173 Cited By 28[Bibtex] [PDF]
[29]	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, 1998: 525~536 Cited By 391[Bibtex]
[28]	Peter L. Bartlett, Tamas Linder, Gabor Lugosi. The Minimax Distortion Redundancy in Empirical Quantizer Design. IEEE Transactions on Information Theory, 1998: 1802~1813 Cited By 31[Bibtex] [PDF]
[27]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. The Importance of Convexity in Learning with Squared Loss. IEEE Transactions on Information Theory, 1998: 1974~1980 Cited By 65[Bibtex] [PDF]
[26]	John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony. Structural Risk Minimization Over Data-Dependent Hierarchies. IEEE Transactions on Information Theory, 1998: 1926~1940 Cited By 362[Bibtex] [PDF]
[25]	Peter L. Bartlett, Tamas Linder, Gabor Lugosi. A Minimax Lower Bound for Empirical Quantizer Design. EuroCOLT'1997. pp.210~222 [Bibtex] [PDF]
[24]	Jonathan Baxter, Peter L. Bartlett. A Result Relating Convex n-Widths to Covering Numbers with some Applications to Neural Networks. EuroCOLT'1997. pp.251~259 Cited By 1[Bibtex]
[23]	Jonathan Baxter, Peter L. Bartlett. The Canonical Distortion Measure in Feature Space and 1-NN Classification. NIPS'1997. Cited By 9[Bibtex]
[22]	Mostefa Golea, Peter L. Bartlett, Wee Sun Lee, Llew Mason. Generalization in Decision Trees and DNF: Does Size Matter?. NIPS'1997. Cited By 27[Bibtex] [PDF]
[21]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes. Neural Computation, 1997: 765~769 [Bibtex]
[20]	Peter L. Bartlett, Sanjeev R. Kulkarni, S. E. Posner. Covering numbers for real-valued function classes. IEEE Transactions on Information Theory, 1997: 1721~1724 Cited By 24[Bibtex]
[19]	Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni. Learning Changing Concepts by Exploiting the Structure of Change. COLT'1996. pp.131~139 Cited By 42[Bibtex] [PDF]
[18]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. The Importance of Convexity in Learning with Squared Loss. COLT'1996. pp.140~146 Cited By 65[Bibtex] [PDF]
[17]	John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony. A Framework for Structural Risk Minimisation. COLT'1996. pp.68~76 Cited By 69[Bibtex] [PDF]
[16]	Peter L. Bartlett. For Valid Generalization the Size of the Weights is More Important than the Size of the Network. NIPS'1996. pp.134~140 Cited By 107[Bibtex]
[15]	Martin Anthony, Peter L. Bartlett, Yuval Ishai, John Shawe-Taylor. Valid Generalisation from Approximate Interpolation. Combinatorics, Probability Computing, 1996: 191~214 Cited By 16[Bibtex] [PDF]
[14]	Peter L. Bartlett, Philip M. Long, Robert C. Williamson. Fat-Shattering and the Learnability of Real-Valued Functions. J. Comput. Syst. Sci., 1996: 434~452 Cited By 98[Bibtex] [PDF]
[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, 1996: 2118~2132 Cited By 123[Bibtex] [PDF]
[12]	Peter L. Bartlett, Philip M. Long. More Theorems about Scale-sensitive Dimensions and Learning. COLT'1995. pp.392~401 Cited By 22[Bibtex] [PDF]
[11]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. On Efficient Agnostic Learning of Linear Combinations of Basis Functions. COLT'1995. pp.369~376 Cited By 19[Bibtex] [PDF]
[10]	Martin Anthony, Peter L. Bartlett. Function learning from interpolation. EuroCOLT'1995. pp.211~221 Cited By 41[Bibtex]
[9]	Adam Kowalczyk, Jacek Szymanski, Peter L. Bartlett, Robert C. Williamson. Examples of learning curves from a modified VC-formalism. NIPS'1995. pp.344~350 Cited By 1[Bibtex] [PDF]
[8]	Peter L. Bartlett, Paul Fischer, Klaus-Uwe Hoffgen. Exploiting Random Walks for Learning. COLT'1994. pp.318~327 Cited By 14[Bibtex] [PDF]
[7]	Peter L. Bartlett, Philip M. Long, Robert C. Williamson. Fat-Shattering and the Learnability of Real-Valued Functions. COLT'1994. pp.299~310 Cited By 98[Bibtex] [PDF]
[6]	Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson. Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes. COLT'1994. pp.362~367 [Bibtex] [PDF]
[5]	Peter L. Bartlett. Lower Bounds on the Vapnik-Chervonenkis Dimension of Multi-Layer Threshold Networks. COLT'1993. pp.144~150 Cited By 19[Bibtex] [PDF]
[4]	Peter L. Bartlett. Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks. Neural Computation, 1993: 371~373 Cited By 17[Bibtex]
[3]	Peter L. Bartlett. Learning With a Slowly Changing Distribution. COLT'1992. pp.243~252 Cited By 32[Bibtex] [PDF]
[2]	Peter L. Bartlett, Robert C. Williamson. Investigating the Distribution Assumptions in the Pac Learning Model. COLT'1991. pp.24~32 Cited By 16[Bibtex]
[1]	Robert C. Williamson, Peter L. Bartlett. Splines, Rational Functions and Neural Networks. NIPS'1991. pp.1040~1047 Cited By 1[Bibtex]