Peter L. Bartlett

Orcid: 0000-0002-8760-3140

Affiliations:
  • University of California at Berkeley, Department of Statistics, CA, USA


According to our database1, Peter L. Bartlett authored at least 232 papers between 1991 and 2024.

Collaborative distances:

Awards

ACM Fellow

ACM Fellow 2018, "For contributions to the theory of machine learning".

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Corrigendum to "Prediction, learning, uniform convergence, and scale-sensitive dimensions" [J. Comput. Syst. Sci. 56 (2) (1998) 174-190].
J. Comput. Syst. Sci., March, 2024

A Diffusion Process Perspective on Posterior Contraction Rates for Parameters.
SIAM J. Math. Data Sci., 2024

Trained Transformers Learn Linear Models In-Context.
J. Mach. Learn. Res., 2024

Sharpness-Aware Minimization and the Edge of Stability.
J. Mach. Learn. Res., 2024

A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data.
CoRR, 2024

Fast Best-of-N Decoding via Speculative Rejection.
CoRR, 2024

FutureFill: Fast Generation from Convolutional Sequence Models.
CoRR, 2024

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization.
CoRR, 2024

Scaling Laws in Linear Regression: Compute, Parameters, and Data.
CoRR, 2024

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization.
CoRR, 2024

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension.
CoRR, 2024

Contextual Bandits with Stage-wise Constraints.
CoRR, 2024

Can a transformer represent a Kalman filter?
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
Proceedings of the Twelfth International Conference on Learning Representations, 2024

A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency.
Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023
Benign overfitting in ridge regression.
J. Mach. Learn. Res., 2023

A Complete Characterization of Linear Estimators for Offline Policy Evaluation.
J. Mach. Learn. Res., 2023

Random Feature Amplification: Feature Learning and Generalization in Neural Networks.
J. Mach. Learn. Res., 2023

The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima.
J. Mach. Learn. Res., 2023

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit.
Proceedings of the International Conference on Algorithmic Learning Theory, 2023

2022
An Efficient Sampling Algorithm for Non-smooth Composite Potentials.
J. Mach. Learn. Res., 2022

The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks.
J. Mach. Learn. Res., 2022

Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency.
CoRR, 2022

Joint Representation Training in Sequential Tasks with Shared Structure.
CoRR, 2022

A Sharp Characterization of Linear Estimators for Offline Policy Evaluation.
CoRR, 2022

Optimal variance-reduced stochastic approximation in Banach spaces.
CoRR, 2022

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Optimal Mean Estimation without a Variance.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Generalization Bounds for Data-Driven Numerical Linear Algebra.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021
Deep learning: a statistical viewpoint.
Acta Numer., May, 2021

High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm.
J. Mach. Learn. Res., 2021

When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks?
J. Mach. Learn. Res., 2021

Failures of Model-dependent Generalization Bounds for Least-norm Interpolation.
J. Mach. Learn. Res., 2021

Parallelizing Contextual Linear Bandits.
CoRR, 2021

Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm.
CoRR, 2021

Near Optimal Policy Optimization via REPS.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On the Theory of Reinforcement Learning with Once-per-Episode Feedback.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Adversarial Examples in Multi-Layer Random ReLU Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Agnostic Learning with Unknown Utilities.
Proceedings of the 12th Innovations in Theoretical Computer Science Conference, 2021

Dropout: Explicit Forms and Capacity Control.
Proceedings of the 38th International Conference on Machine Learning, 2021

Towards a Dimension-Free Understanding of Adaptive Linear Control.
Proceedings of the Conference on Learning Theory, 2021

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
Proceedings of the Conference on Learning Theory, 2021

Stochastic Bandits with Linear Constraints.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems.
J. Mach. Learn. Res., 2020

Regret Bound Balancing and Elimination for Model Selection in Bandits and RL.
CoRR, 2020

Optimal Robust Linear Regression in Nearly Linear Time.
CoRR, 2020

On Thompson Sampling with Langevin Algorithms.
CoRR, 2020

Oracle lower bounds for stochastic gradient sampling algorithms.
CoRR, 2020

Self-Distillation Amplifies Regularization in Hilbert Space.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Preference learning along multiple criteria: A game-theoretic perspective.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Greedy Convex Ensemble.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

On Approximate Thompson Sampling with Langevin Algorithms.
Proceedings of the 37th International Conference on Machine Learning, 2020

Accelerated Message Passing for Entropy-Regularized MAP Inference.
Proceedings of the 37th International Conference on Machine Learning, 2020

Stochastic Gradient and Langevin Processes.
Proceedings of the 37th International Conference on Machine Learning, 2020

On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration.
Proceedings of the Conference on Learning Theory, 2020

OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Langevin Monte Carlo without smoothness.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks.
Neural Comput., 2019

Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks.
J. Mach. Learn. Res., 2019

Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing.
CoRR, 2019

Hebbian Synaptic Modifications in Spiking Neurons that Learn.
CoRR, 2019

Learning Near-optimal Convex Combinations of Basis Models with Generalization Guarantees.
CoRR, 2019

Bayesian Robustness: A Nonasymptotic Viewpoint.
CoRR, 2019

Quantitative W<sub>1</sub> Convergence of Langevin-Like Stochastic Processes with Non-Convex Potential State-Dependent Noise.
CoRR, 2019

Benign Overfitting in Linear Regression.
CoRR, 2019

Testing Markov Chains without Hitting.
CoRR, 2019

Is There an Analog of Nesterov Acceleration for MCMC?
CoRR, 2019

Quantitative Central Limit Theorems for Discrete Stochastic Processes.
CoRR, 2019

Large-Scale Markov Decision Problems via the Linear Programming Dual.
CoRR, 2019

Rademacher Complexity for Adversarially Robust Generalization.
Proceedings of the 36th International Conference on Machine Learning, 2019

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

Online learning with kernel losses.
Proceedings of the 36th International Conference on Machine Learning, 2019

Scale-free adaptive planning for deterministic dynamics & discounted rewards.
Proceedings of the 36th International Conference on Machine Learning, 2019

Fast Mean Estimation with Sub-Gaussian Rates.
Proceedings of the Conference on Learning Theory, 2019

Testing Symmetric Markov Chains Without Hitting.
Proceedings of the Conference on Learning Theory, 2019

A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption.
Proceedings of the Algorithmic Learning Theory, 2019

Best of many worlds: Robust model selection for online supervised learning.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation.
CoRR, 2018

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting.
CoRR, 2018

Representing smooth functions as compositions of near-identity functions with implications for deep network optimization.
CoRR, 2018

Horizon-Independent Minimax Linear Regression.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates.
Proceedings of the 35th International Conference on Machine Learning, 2018

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo.
Proceedings of the 35th International Conference on Machine Learning, 2018

Gradient descent with identity initialization efficiently learns positive definite linear transformations.
Proceedings of the 35th International Conference on Machine Learning, 2018

Two Approximate Dynamic Programming Algorithms for Managing Complete SIS Networks.
Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies, 2018

Underdamped Langevin MCMC: A non-asymptotic analysis.
Proceedings of the Conference On Learning Theory, 2018

Best of both worlds: Stochastic & adversarial best-arm identification.
Proceedings of the Conference On Learning Theory, 2018

Convergence of Langevin MCMC in KL-divergence.
Proceedings of the Algorithmic Learning Theory, 2018

Gradient Diversity: a Key Ingredient for Scalable Distributed Learning.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

FLAG n' FLARE: Fast Linearly-Coupled Adaptive Gradient Methods.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017
Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction.
IEEE Trans. Inf. Theory, 2017

Approximate and Stochastic Greedy Optimization.
CoRR, 2017

Gradient Diversity Empowers Distributed Learning.
CoRR, 2017

Acceleration and Averaging in Stochastic Descent Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Alternating minimization for dictionary learning with random initialization.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Spectrally-normalized margin bounds for neural networks.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Recovery Guarantees for One-hidden-layer Neural Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Hit-and-Run for Sampling and Planning in Non-Convex Spaces.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

Fast-Tracking Stationary MOMDPs for Adaptive Management Problems.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning.
CoRR, 2016

FLAG: Fast Linearly-Coupled Adaptive Gradient Method.
CoRR, 2016

Adaptive Averaging in Accelerated Descent Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Improved Learning Complexity in Combinatorial Pure Exploration Bandits.
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

A Fast and Reliable Policy Improvement Algorithm.
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015
Accelerated Mirror Descent in Continuous and Discrete Time.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Minimax Time Series Prediction.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Minimax Fixed-Design Linear Regression.
Proceedings of The 28th Conference on Learning Theory, 2015

2014
Bounding Embeddings of VC Classes into Maximum Classes.
CoRR, 2014

Efficient Minimax Strategies for Square Loss Games.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Large-Margin Convex Polytope Machine.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Prediction with Limited Advice and Multiarmed Bandits with Paid Observations.
Proceedings of the 31th International Conference on Machine Learning, 2014

Linear Programming for Large-Scale Markov Decision Problems.
Proceedings of the 31th International Conference on Machine Learning, 2014

Tracking Adversarial Targets.
Proceedings of the 31th International Conference on Machine Learning, 2014

2013
Advice-Efficient Prediction with Expert Advice
CoRR, 2013

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions
CoRR, 2013

How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Open Problem: Adversarial Multiarmed Bandits with Limited Advice.
Proceedings of the COLT 2013, 2013

Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families.
Proceedings of the COLT 2013, 2013

2012
Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization.
IEEE Trans. Inf. Theory, 2012

A Learning-Based Approach to Reactive Security.
IEEE Trans. Dependable Secur. Comput., 2012

Randomized Smoothing for Stochastic Optimization.
SIAM J. Optim., 2012

Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning.
J. Priv. Confidentiality, 2012

Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction with Jeffreys Prior.
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Oracle inequalities for computationally adaptive model selection
CoRR, 2012

The Optimality of Jeffreys Prior for Online Density Estimation and the Asymptotic Normality of Maximum Likelihood Estimators.
Proceedings of the COLT 2012, 2012

Randomized smoothing for (parallel) stochastic optimization.
Proceedings of the 51th IEEE Conference on Decision and Control, 2012

2011
Oracle inequalities for computationally budgeted model selection.
Proceedings of the COLT 2011, 2011

Blackwell Approachability and No-Regret Learning are Equivalent.
Proceedings of the COLT 2011, 2011

Online and Batch Learning Algorithms for Data with Missing Features
CoRR, 2011

Learning with Missing Features.
Proceedings of the UAI 2011, 2011

2010
Optimal Allocation Strategies for the Dark Pool Problem.
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Corrigendum to "Shifting: One-inclusion mistake bounds and sample compression" [J. Comput. System Sci 75 (1) (2009) 37-59].
J. Comput. Syst. Sci., 2010

Blackwell Approachability and Low-Regret Learning are Equivalent
CoRR, 2010

Learning to act in uncertain environments: technical perspective.
Commun. ACM, 2010

A Unifying View of Multiple Kernel Learning.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2010

Implicit Online Learning.
Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

Optimal Online Prediction in Adversarial Environments.
Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

A Regularization Approach to Metrical Task Systems.
Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

2009
Multiview point cloud kernels for semisupervised learning [Lecture Notes].
IEEE Signal Process. Mag., 2009

Shifting: One-inclusion mistake bounds and sample compression.
J. Comput. Syst. Sci., 2009

REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs.
Proceedings of the UAI 2009, 2009

Information-theoretic lower bounds on the oracle complexity of convex optimization.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

A Stochastic View of Optimal Regret through Minimax Duality.
Proceedings of the COLT 2009, 2009

2008
Correction to "The Importance of Convexity in Learning With Squared Loss".
IEEE Trans. Inf. Theory, 2008

Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks.
J. Mach. Learn. Res., 2008

Classification with a Reject Option using a Hinge Loss.
J. Mach. Learn. Res., 2008

High-Probability Regret Bounds for Bandit Online Linear Optimization.
Proceedings of the 21st Annual Conference on Learning Theory, 2008

Optimal Stragies and Minimax Lower Bounds for Online Convex Games.
Proceedings of the 21st Annual Conference on Learning Theory, 2008

Open problems in the security of learning.
Proceedings of the 1st ACM Workshop on Security and Artificial Intelligence, 2008

2007
On the Consistency of Multiclass Classification Methods.
J. Mach. Learn. Res., 2007

The Rademacher Complexity of Co-Regularized Kernel Classes.
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

AdaBoost is Consistent.
J. Mach. Learn. Res., 2007

Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results.
J. Mach. Learn. Res., 2007

Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Adaptive Online Gradient Descent.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Online discovery of similarity mappings.
Proceedings of the Machine Learning, 2007

Bounded Parameter Markov Decision Processes with Average Reward Criterion.
Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

Multitask Learning with Expert Advice.
Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

2006
Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Sample Complexity of Policy Search with Known Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

2004
Learning the Kernel Matrix with Semidefinite Programming.
J. Mach. Learn. Res., 2004

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.
J. Mach. Learn. Res., 2004

Exponentiated Gradient Algorithms for Large-margin Structured Classification.
Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results.
Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

Local Complexities for Empirical Risk Minimization.
Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

2003
Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates.
Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003

2002
Covering numbers for support vector machines.
IEEE Trans. Inf. Theory, 2002

Hardness results for neural network approximation problems.
Theor. Comput. Sci., 2002

Model Selection and Error Estimation.
Mach. Learn., 2002

Rademacher and Gaussian Complexities: Risk Bounds and Structural Results.
J. Mach. Learn. Res., 2002

Generalization Error of Combined Classifiers.
J. Comput. Syst. Sci., 2002

Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning.
J. Comput. Syst. Sci., 2002

Exploiting Random Walks for Learning.
Inf. Comput., 2002

An Introduction to Reinforcement Learning Theory: Value Function Methods.
Proceedings of the Advanced Lectures on Machine Learning, 2002

Learning the Kernel Matrix with Semi-Definite Programming.
Proceedings of the Machine Learning, 2002

Localized Rademacher Complexities.
Proceedings of the Computational Learning Theory, 2002

Neural Network Learning - Theoretical Foundations.
Cambridge University Press, ISBN: 978-0-521-57353-5, 2002

2001
Experiments with Infinite-Horizon, Policy-Gradient Estimation.
J. Artif. Intell. Res., 2001

Infinite-Horizon Policy-Gradient Estimation.
J. Artif. Intell. Res., 2001

2000
New Support Vector Algorithms.
Neural Comput., 2000

Improved Generalization Through Explicit Optimization of Margins.
Mach. Learn., 2000

Learning Changing Concepts by Exploiting the Structure of Change.
Mach. Learn., 2000

Profiling in the ASP codesign environment.
J. Syst. Archit., 2000

Function Learning From Interpolation.
Comb. Probab. Comput., 2000

Direct iterative tuning via spectral analysis.
Autom., 2000

Sparse Greedy Gaussian Process Regression.
Proceedings of the Advances in Neural Information Processing Systems 13, 2000

Direct gradient-based reinforcement learning.
Proceedings of the IEEE International Symposium on Circuits and Systems, 2000

Reinforcement Learning in POMDP's via Direct Gradient Ascent.
Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford University, Stanford, CA, USA, June 29, 2000

Stochastic optimization of controlled partially observable Markov decision processes.
Proceedings of the 39th IEEE Conference on Decision and Control, 2000

1999
Boosting Algorithms as Gradient Descent.
Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999

1998
Structural Risk Minimization Over Data-Dependent Hierarchies.
IEEE Trans. Inf. Theory, 1998

The Importance of Convexity in Learning with Squared Loss.
IEEE Trans. Inf. Theory, 1998

The Minimax Distortion Redundancy in Empirical Quantizer Design.
IEEE Trans. Inf. Theory, 1998

The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network.
IEEE Trans. Inf. Theory, 1998

Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks.
Neural Comput., 1998

Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions.
J. Comput. Syst. Sci., 1998

Optimal controller properties from closed-loop experiments.
Autom., 1998

Shrinking the Tube: A New Support Vector Regression Algorithm.
Proceedings of the Advances in Neural Information Processing Systems 11, [NIPS Conference, Denver, Colorado, USA, November 30, 1998

Direct Optimization of Margins Improves Generalization in Combined Classifiers.
Proceedings of the Advances in Neural Information Processing Systems 11, [NIPS Conference, Denver, Colorado, USA, November 30, 1998

1997
Covering numbers for real-valued function classes.
IEEE Trans. Inf. Theory, 1997

Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes'.
Neural Comput., 1997

Generalization in Decision Trees and DNF: Does Size Matter?
Proceedings of the Advances in Neural Information Processing Systems 10, 1997

The Canonical Distortion Measure in Feature Space and 1-NN Classification.
Proceedings of the Advances in Neural Information Processing Systems 10, 1997

A Result Relating Convex <i>n</i>-Widths to Covering Numbers with some Applications to Neural Networks.
Proceedings of the Computational Learning Theory, Third European Conference, 1997

A Minimax Lower Bound for Empirical Quantizer Design.
Proceedings of the Computational Learning Theory, Third European Conference, 1997

1996
Efficient agnostic learning of neural networks with bounded fan-in.
IEEE Trans. Inf. Theory, 1996

The VC Dimension and Pseudodimension of Two-Layer Neural Networks with Discrete Inputs.
Neural Comput., 1996

Fat-Shattering and the Learnability of Real-Valued Functions.
J. Comput. Syst. Sci., 1996

Valid Generalisation from Approximate Interpolation.
Comb. Probab. Comput., 1996

For Valid Generalization the Size of the Weights is More Important than the Size of the Network.
Proceedings of the Advances in Neural Information Processing Systems 9, 1996

A Framework for Structural Risk Minimisation.
Proceedings of the Ninth Annual Conference on Computational Learning Theory, 1996

1995
Lower Bounds on the VC Dimension of Smoothly Parameterized Function Classes.
Neural Comput., 1995

Examples of learning curves from a modified VC-formalism.
Proceedings of the Advances in Neural Information Processing Systems 8, 1995

On Efficient Agnostic Learning of Linear Combinations of Basis Functions.
Proceedings of the Eigth Annual Conference on Computational Learning Theory, 1995

More Theorems about Scale-sensitive Dimensions and Learning.
Proceedings of the Eigth Annual Conference on Computational Learning Theory, 1995

1994
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes.
Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, 1994

1993
Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks.
Neural Comput., 1993

Lower Bounds on the Vapnik-Chervonenkis Dimension of Multi-Layer Threshold Networks.
Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, 1993

1992
Computational learning theory and neural network learning
PhD thesis, 1992

Using random weights to train multilayer networks of hard-limiting units.
IEEE Trans. Neural Networks, 1992

Learning With a Slowly Changing Distribution.
Proceedings of the Fifth Annual ACM Conference on Computational Learning Theory, 1992

1991
Splines, Rational Functions and Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 4, 1991

Investigating the Distribution Assumptions in the Pac Learning Model.
Proceedings of the Fourth Annual Workshop on Computational Learning Theory, 1991


  Loading...