Nathan Srebro
Identifiers
- name variant Nathan Srebro 0.60 · backfill
Papers (75)
- Learning to Think from Multiple Thinkers cs.LG · 2026 · author #3
- Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory cs.LG · 2019 · author #2
- Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models stat.ML · 2019 · author #4
- Semi-Cyclic Stochastic Gradient Descent cs.LG · 2019 · author #4
- How do infinite width bounded norm networks look in function space? cs.LG · 2019 · author #4
- The Complexity of Making the Gradient Small in Stochastic Convex Optimization cs.LG · 2019 · author #4
- VC Classes are Adversarially Robustly Learnable, but Only Improperly cs.LG · 2019 · author #3
- On preserving non-discrimination when combining expert advice cs.LG · 2018 · author #4
- Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints cs.LG · 2018 · author #4
- A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates math.OC · 2018 · author #3
- Implicit Bias of Gradient Descent on Linear Convolutional Networks cs.LG · 2018 · author #4
- Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks cs.LG · 2018 · author #5
- Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization math.OC · 2018 · author #5
- The Everlasting Database: Statistical Validity at a Fair Price cs.LG · 2018 · author #4
- Convergence of Gradient Descent on Separable Data stat.ML · 2018 · author #5
- Distributed Stochastic Multi-Task Learning with Graph Regularization stat.ML · 2018 · author #4
- An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning math.OC · 2017 · author #4
- Stochastic Nonconvex Optimization with Large Minibatches cs.LG · 2017 · author #2
- Lower Bound for Randomized First Order Convex Optimization math.OC · 2017 · author #2
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks cs.LG · 2017 · author #3
- Exploring Generalization in Deep Learning cs.LG · 2017 · author #4
- Implicit Regularization in Matrix Factorization stat.ML · 2017 · author #5
- The Marginal Value of Adaptive Gradient Methods in Machine Learning stat.ML · 2017 · author #4
- Geometry of Optimization and Implicit Regularization in Deep Learning cs.LG · 2017 · author #4
- Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis cs.LG · 2017 · author #3
- Efficient coordinate-wise leading eigenvector computation cs.NA · 2017 · author #4
- Stochastic Approximation for Canonical Correlation Analysis cs.LG · 2017 · author #4
- Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox cs.LG · 2017 · author #3
- Learning Non-Discriminatory Predictors cs.LG · 2017 · author #4
- Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data cs.LG · 2016 · author #5
- Equality of Opportunity in Supervised Learning cs.LG · 2016 · author #3
- Tight Complexity Bounds for Optimizing Composite Objectives math.OC · 2016 · author #2
- Efficient Distributed Learning with Sparsity stat.ML · 2016 · author #3
- Global Optimality of Local Search for Low Rank Matrix Recovery stat.ML · 2016 · author #3
- Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations cs.LG · 2016 · author #4
- Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis cs.LG · 2016 · author #4
- On Data Dependence in Distributed Stochastic Optimization math.OC · 2016 · author #3
- Distributed Multi-Task Learning with Shared Representation cs.LG · 2016 · author #3
- Reducing Runtime by Recycling Samples cs.LG · 2016 · author #3
- Data-Dependent Path Normalization in Neural Networks cs.LG · 2015 · author #4
- Fast and Scalable Structural SVM with Slack Rescaling cs.LG · 2015 · author #3
- Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations cs.LG · 2015 · author #4
- Distributed Multitask Learning stat.ML · 2015 · author #3
- Normalized Hierarchical SVM cs.LG · 2015 · author #3
- Distributed Mini-Batch SDCA cs.LG · 2015 · author #3
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks cs.LG · 2015 · author #3
- Norm-Based Capacity Control in Neural Networks cs.LG · 2015 · author #3
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning cs.LG · 2014 · author #3
- On Symmetric and Asymmetric LSHs for Inner Product Search stat.ML · 2014 · author #2
- Clustering, Hamming Embedding, Generalized LSH and the Max Norm cs.LG · 2014 · author #3
- Communication Efficient Distributed Optimization using an Approximate Newton-type Method cs.LG · 2013 · author #2
- The Power of Asymmetry in Binary Hashing cs.LG · 2013 · author #5
- Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm math.NA · 2013 · author #2
- Stochastic Optimization of PCA with Capped MSG stat.ML · 2013 · author #3
- Auditing: Active Learning with Outcome-Dependent Query Costs cs.LG · 2013 · author #3
- Mini-Batch Primal and Dual Methods for SVMs cs.LG · 2013 · author #4
- Maximum Likelihood Bounded Tree-Width Markov Networks cs.LG · 2013 · author #1
- Learning Sparse Low-Threshold Linear Classifiers stat.ML · 2012 · author #3
- Matrix reconstruction with the local max norm stat.ML · 2012 · author #2
- Complexity of Inference in Graphical Models cs.DS · 2012 · author #2
- PRISMA: PRoximal Iterative SMoothing Algorithm math.OC · 2012 · author #3
- Sparse Prediction with the $k$-Support Norm stat.ML · 2012 · author #3
- Distribution-Dependent Sample Complexity of Large Margin Learning stat.ML · 2012 · author #2
- The Kernelized Stochastic Batch Perceptron cs.LG · 2012 · author #3
- Clustering using Max-norm Constrained Optimization cs.LG · 2012 · author #2
- Semi-supervised Learning with Density Based Distances cs.LG · 2012 · author #3
- Explicit Approximations of the Gaussian Kernel cs.AI · 2011 · author #3
- Fast-rate and optimistic-rate error bounds for L1-regularized regression math.ST · 2011 · author #2
- On the Universality of Online Mirror Descent cs.LG · 2011 · author #1
- Better Mini-Batch Algorithms via Accelerated Gradient Methods cs.LG · 2011 · author #3
- Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions cs.LG · 2011 · author #4
- Concentration-Based Guarantees for Low-Rank Matrix Reconstruction cs.LG · 2011 · author #2
- Tight Sample Complexity of Large-Margin Learning cs.LG · 2010 · author #2
- Optimistic Rates for Learning with a Smooth Loss cs.LG · 2010 · author #1
- Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm cs.LG · 2010 · author #2
Mentions
- 1303.2314 #4 · backfill · confidence 0.70 Nathan Srebro
- 1301.2311 #1 · backfill · confidence 0.70 Nathan Srebro
- 1212.3276 #3 · backfill · confidence 0.70 Nathan Srebro
- 1210.5196 #2 · backfill · confidence 0.70 Nathan Srebro
- 1206.3240 #2 · backfill · confidence 0.70 Nathan Srebro
- 1206.2372 #3 · backfill · confidence 0.70 Nathan Srebro
- 1204.5043 #3 · backfill · confidence 0.70 Nathan Srebro
- 1204.1276 #2 · backfill · confidence 0.70 Nathan Srebro
- 1204.0566 #3 · backfill · confidence 0.70 Nathan Srebro
- 1202.5598 #2 · backfill · confidence 0.70 Nathan Srebro
- 1202.3702 #3 · backfill · confidence 0.70 Nathan Srebro
- 1109.4603 #3 · backfill · confidence 0.70 Nathan Srebro
- 1108.0373 #2 · backfill · confidence 0.70 Nathan Srebro
- 1107.4080 #1 · backfill · confidence 0.70 Nathan Srebro
- 1106.4574 #3 · backfill · confidence 0.70 Nathan Srebro
- 1106.4251 #4 · backfill · confidence 0.70 Nathan Srebro
- 1102.3923 #2 · backfill · confidence 0.70 Nathan Srebro
- 1011.5053 #2 · backfill · confidence 0.70 Nathan Srebro
- 1009.3896 #1 · backfill · confidence 0.70 Nathan Srebro
- 1002.2780 #2 · backfill · confidence 0.70 Nathan Srebro
Frequent Coauthors
- Behnam Neyshabur 14 shared papers
- Jialei Wang 10 shared papers
- Blake Woodworth 9 shared papers
- Ruslan Salakhutdinov 8 shared papers
- Ohad Shamir 6 shared papers
- Suriya Gunasekar 6 shared papers
- Weiran Wang 6 shared papers
- Andrew Cotter 5 shared papers
- Karthik Sridharan 5 shared papers
- Mladen Kolar 5 shared papers
- Rina Foygel 5 shared papers
- Srinadh Bhojanapalli 5 shared papers
- Daniel Soudry 4 shared papers
- Ryota Tomioka 4 shared papers
- Sivan Sabato 4 shared papers
- Dan Garber 3 shared papers
- Jason D. Lee 3 shared papers
- Martin Tak\'a\v{c} 3 shared papers
- Raman Arora 3 shared papers
- Tong Zhang 3 shared papers