Stochastic Optimization for Machine Learning International Conference on Machine Learning (ICML), Haifa, Israel, 2010
Linear Programming in Bounded Tree-width Markov Networks Workshop on Mathematical Programming in Data Mining and Machine Learning, Ontario, Canada, 2005
Semidefinite optimization with applications in sparse multivariate statistics Workshop on Mathematical Programming in Data Mining and Machine Learning, Banff, Alberta, 2007
Maximum Margin Matrix Factorization using Smooth Semidefinite Optimization INFORMS Annual Meeting, San Francisco, USA, 2005
Kernel and Rich Regimes in Deep Learning, Institute for Advanced Study, 2019
Optimization's Hidden Gift to Learning: Implicit Regularization, Data Science Colloquim, ENS-CFM, 2019
Can You Help Us Understand Deep Learning, Gotham City MLX Physics Workshop, 2019
Implicit Regularization II, Deep Learning Boot Camp, 2019
Implicit Regularization I, Deep Learning Boot Camp, 2019
Theoretical Perspectives on Deep Learning, NAS Colloquia, 2019
Economic Models I, The Conference on Fairness, Accountability, and Transparency (FAT*), 2019
Tutorial: Optimization Methods from a Machine Learning Perspective, KITP, UCSB, 2019
Ethics, Fairness, and Bias, Data Science for Social Good (DSSG) Conference, 2019
The Implicit Bias of Linear Convolutional Networks, Foundations of Machine Learning Reunion, 2018
Optimization's Untold Gift to Learning: Implicit Regularization, Optimization, Statistics and Uncertainty, 2017
Geometry, Optimization and Generalization in Multilayer Networks, Representation Learning, 2017
On Symmetric and Asymmentric LSHs for inner Product Search, 32nd International Conference on Machine Learning (ICML), 2015 Paper: arXiv
The Power of Asymmetry in Binary Hashing, Technion, 2014 Paper: arXiv
Optimistic Rates, NIPS Workshops, Lake Tahoe, 2013
Learning with Matrix Parameters, NIPS Workshops, Lake Tahoe, 2013
More Data Less Work: Runtime as a Monotonically Decreasing Function of Data Set Size, Machine Learning Summer School (MLSS), Chicago, 2009
Learning Bounds for Support Vector Machines with Learned Kernels, NIPS Workshop on Kernel Learning: Automatic Selection of Optimal Kernels, Whistler, 2008 Paper: Springer
Generalization Bounds for Indefinite Kernel Machines, NIPS Workshop on New Challenges in Theoretical Machine Learning: Learning with Data-dependent Concept Spaces, Whistler, 2008
SVM Optimization: Inverse Dependence on Training Set Size, ICML Award Paper Joint Session, 2008
Stability and Convergence, Workshop on Stability and Resampling Methods for Clustering, Tübingen, 2007