Peter Bartlett's Talks

Optimization in highdimensional prediction
NonLinear and High Dimensional Inference, IHP, Paris, 37 October 2022.
[slides]

Benign Overfitting in Linear Regression
AI Institute "Geometry of Deep Learning",
Microsoft Research Redmond, August 2628, 2019.
[slides]
Frontiers of
Deep Learning Workshop, Simons Institute for the Theory of Computing, UC
Berkeley, July 1518, 2019.
[slides]
Google, Mountain View, June 17, 2019.
[slides]
Peter G.
Hall Conference 2019: Statistics and Machine Learning, Department of
Statistics, UC Davis, May 1011, 2019.
[slides]
NeurIPS 2021,
December 8, 2021.
[slides]

Tutorial: Generalization in Deep Learning
Deep Learning Boot Camp,
Simons Institute for the Theory of Computing, May 2831, 2019. With Sasha Rakhlin.
[slides]

Optimizing Probability Distributions for Learning:
Sampling meets Optimization
University of
California at Los Angeles Mathematics Colloquium
May 2, 2019.
[slides]
University of
Southern California MASCLE Machine Learning Seminar
April 16, 2019.
[slides]
BAIR/BDD Workshop. March 25, 2019.
[slides]
University of
Pennsylvania PRiML Seminar
February 24, 2019.
[slides]

Generalization and Optimization in Deep Networks
YES X :
"Understanding Deep Learning: Generalization, Approximation and
Optimization", Eurandom
March 1922, 2019.
[slides: 1,
2,
3]

Accurate Prediction from Interpolation: A New Challenge for
Statistical Learning Theory
NAS Colloquium: The Science of Deep Learning
March 1314, 2019.
[slides]

Efficient Optimal Strategies for Prediction Games
University of
Queensland Statistics, Modelling and Operations Research Seminar
October 4, 2018.
[slides]

Representation, Optimization and Generalization in Deep Learning
BayLearn2018 Bay Area Machine Learning Symposium,
Facebook, October 11, 2018.
[slides]
DIMACS/TRIPODS Workshop on Optimization in Machine Learning,
Lehigh University, August 1315, 2018.
[slides]
Future Challenges in Statistical Scalability,
Isaac Newton Institute for Mathematical Sciences, June 27, 2018.
[slides]
Foundations of Machine Learning Reunion Workshop,
Simons Institute for the Theory of Computing, June 7, 2018.
[slides]
Bridging
Mathematical Optimization, Information Theory, and Data Science,
Princeton Center for Statistics and Machine Learning, May 14, 2018.
[slides]
Modern
Challenges of Learning Theory,
Centre de Recherches Mathematiques, April 23, 2018.
[slides]
University of
Queensland Maths Colloquium January 25, 2018.
[slides]
IEOR Department Colloquium. October 9, 2017.
[slides]

Statistical properties of deep networks
JSM session on Theory at the Intersection of Machine
Learning and Statistics August 2, 2018.
[slides]
NIPS
Workshop on Deep Learning Theory and Practice. December 9, 2017.
[slides]
BAIR/BDD Workshop. November 28, 2017.
[slides]
Machine Learning at Berkeley. October 5, 2017.
[slides]

The optimal strategy for a linear regression game
[slides]
Dagstuhl seminar. June 1923, 2017.

Topics in prediction and learning
[Lecture
1,
Lectures 2 and 3,
Lecture 4,
references]
ENSAE/CREST. Feb 27Mar 9, 2017.

Efficient Optimal Strategies for Universal Prediction.
[Slides: pdf]
Stochastics and Statistics Seminar,
MIT. December 11, 2015.

Prediction and sequential decision problems in adversarial
environments.
[Slides: pdf]
CDAR Symposium.
Berkeley. October 16, 2015.

Efficient minimax strategies for online prediction.
[Slides: pdf]
ITA.
February 6, 2015.
Caltech. February 9, 2015.

Learning in Markov decision problems.
[Slides: pdf]
[Linear bandits survey slides: pdf]
UCLA.
November 10, 2014.

Model selection and computational oracle inequalities
for large scale problems.
[Slides: pdf]
Workshop on Algorithms for Modern Massive Data Sets
Stanford University.
July 10  13, 2012.

Large scale model selection and computational oracle inequalities
[Slides: pdf]
Conference on Statistical Learning and Data Mining
Rackham Graduate School, University of Michigan, Ann Arbor, MI,
June 5  7, 2012.

Online Prediction
[Slides: pdf]
[Lecture notes: pdf]
Learning Theory: State of the Art
Institut Henri Poincare, Paris, May 911, 2011.

Optimal online prediction in adversarial environments
[Slides: pdf]
The Second Asian Conference on Machine Learning
Tokyo Institute of Technology, Tokyo, Japan, November 810, 2010.

An online allocation problem: Dark pools
[Slides: pdf]
The Mathematics of Ranking
American Institute of Mathematics, Palo Alto, California, August 1620, 2010.

l1regularized linear regression: persistence and oracle inequalities
[Slides: pdf]
Probability and Statistics  an international conference in honor of
P.L. Hsu's 100th birthday
Peking University, Beijing, China. July 6, 2010.
10th International Vilnius Conference on Probability Theory and
Mathematical Statistics. June 30, 2010.

Convex methods for classification
[Slides: pdf]
IMS Medallion Lecture. June 2008.

Optimism in Sequential Decision Making
[Slides: pdf]
UC Berkeley Statistics. September 2007.

Consistency of AdaBoost
[Slides: pdf]
Google. May 2007.

AdaBoost and other Large Margin Classifiers:
Convexity in Classification
[Slides: pdf]
Presented at DASP 2006. December 2006.

Convex methods for classification
[Slides: pdf]

AdaBoost and other Large Margin Classifiers:
Convexity in Classification
[Slides: ps]
Presented at the Institute
of Statistical Science, Academia
Sinica, Taipei, Taiwan., July 31, 2006.

AdaBoost is Universally Consistent
[Slides: ps,
pdf]
Presented at the
2006 Summer Institute
held by the Institute of Information Science (IIS), Academia Sinica,
Taipei, Taiwan., August 3, 2006.

Regression Methods for Pattern Classification:
Statistical Properties of Large Margin Classifiers
[Slides: ps,
pdf]
Presented at
Mathematisches Forschungsinstitut
Oberwolfach, October 1622, 2005.

Empirical Minimization and Risk Bounds
[Slides: ps]

Statistical Properties of Large Margin Classifiers
[Slides: ps,
pdf]

Large Margin Classifiers: Convexity and Classification
[Slides: ps,
pdf]

Large Margin Methods for Structured Classification: Exponentiated
Gradient Algorithms
[Slides: ps,
ps.gz]

Local Rademacher Averages and Empirical Minimization
[Slides: ps,
pdf]

The Role of Convexity in Prediction Problems.
[Slides: ps,
ps.gz;
Handouts: ps,
ps.gz]
Presented at
UC Berkeley EECS Joint Colloquium Distinguished Lecture Series,
September 17, 2003.

Prediction Algorithms: Complexity, Concentration, and Convexity.
[Slides: ps,
ps.gz;
Handouts: ps,
ps.gz]
Presented at
SYSID2003: 13th IFAC Symposium on System
Identification, Rotterdam, The Netherlands, 2729 August, 2003.
See:
Extended abstract.

Convexity, Classification, and Risk Bounds.
[Slides: ps,
ps.gz;
Handouts: ps,
ps.gz]
Presented at
Workshop
on Advances in Machine Learning, Montreal, Canada, June 811,
2003, and
AMS/IMS/SIAM Joint
Summer Research Conference on Machine Learning, Statistics, and
Discovery, Snowbird, Utah, June 2226, 2003.
See:
Convexity, classification, and risk bounds.
Peter L. Bartlett, Michael I. Jordan and Jon D. McAuliffe.
Technical Report 638, Department of Statistics, U.C. Berkeley,
2003.
 NIPS'98 Tutorial
(an introduction to learning theory)
Last update: Mon Oct 9 23:20:27 PDT 2006