| Efficient Learning of CNNs using Patch Based Features. | 0 | 0.34 | 2022 |
| Computational Separation Between Convolutional and Fully-Connected Networks | 0 | 0.34 | 2021 |
| The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. | 0 | 0.34 | 2021 |
| The Implicit Bias of Depth: How Incremental Learning Drives Generalization | 0 | 0.34 | 2020 |
| Proving the Lottery Ticket Hypothesis: Pruning is All You Need | 0 | 0.34 | 2020 |
| The Implications of Local Correlation on Learning Some Deep Functions | 0 | 0.34 | 2020 |
| Decoupling Gating from Linearity. | 0 | 0.34 | 2019 |
| Vision Zero: on a Provable Method for Eliminating Roadway Accidents without Compromising Traffic Throughput. | 0 | 0.34 | 2019 |
| Is Deeper Better only when Shallow is Good? | 1 | 0.36 | 2019 |
| A Provably Correct Algorithm for Deep Learning that Actually Works. | 4 | 0.39 | 2018 |
| Decoupling "when to update" from "how to update". | 16 | 0.61 | 2017 |
| Weight Sharing is Crucial to Succesful Optimization. | 3 | 0.42 | 2017 |
| SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data. | 31 | 0.86 | 2017 |
| Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization. | 2 | 0.41 | 2017 |
| Failures of Gradient-Based Deep Learning. | 25 | 0.99 | 2017 |
| On a Formal Model of Safe and Scalable Self-driving Cars. | 21 | 1.38 | 2017 |
| Effective Semisupervised Learning on Manifolds. | 0 | 0.34 | 2017 |
| Tightening the Sample Complexity of Empirical Risk Minimization via Preconditioned Stability. | 0 | 0.34 | 2016 |
| Minimizing the Maximal Loss: How and Why? | 7 | 0.54 | 2016 |
| SDCA without Duality, Regularization, and Individual Convexity. | 20 | 0.93 | 2016 |
| Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving. | 36 | 1.67 | 2016 |
| On Lower and Upper Bounds in Smooth and Strongly Convex Optimization. | 0 | 0.34 | 2016 |
| Long-term Planning by Short-term Prediction. | 7 | 0.55 | 2016 |
| Faster Low-rank Approximation using Adaptive Gap-based Preconditioning. | 0 | 0.34 | 2016 |
| Subspace Learning with Partial Information. | 0 | 0.34 | 2016 |
| Solving Ridge Regression using Sketched Preconditioned SVRG. | 7 | 0.45 | 2016 |
| Learning a Metric Embedding for Face Recognition using the Multibatch Method. | 9 | 0.50 | 2016 |
| Distribution Free Learning with Local Queries. | 0 | 0.34 | 2016 |
| On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training. | 11 | 0.59 | 2016 |
| Faster SGD Using Sketched Conditioning | 2 | 0.39 | 2015 |
| On Lower and Upper Bounds for Smooth and Strongly Convex Optimization Problems. | 0 | 0.34 | 2015 |
| SDCA without Duality. | 22 | 1.08 | 2015 |
| Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization. | 124 | 4.86 | 2014 |
| SelfieBoost: A Boosting Algorithm for Deep Learning. | 3 | 0.42 | 2014 |
| The Complexity of Learning Halfspaces using Generalized Linear Methods. | 3 | 0.39 | 2014 |
| On the Computational Efficiency of Training Neural Networks. | 36 | 2.11 | 2014 |
| Complexity theoretic limitations on learning DNF's. | 24 | 0.85 | 2014 |
| The Sample Complexity of Subspace Learning with Partial Information. | 2 | 0.41 | 2014 |
| Efficient active learning of halfspaces: an aggressive approach | 3 | 0.39 | 2013 |
| More data speeds up training time in learning halfspaces over sparse vectors. | 16 | 0.61 | 2013 |
| Stochastic dual coordinate ascent methods for regularized loss | 23 | 1.21 | 2013 |
| A Provably Efficient Algorithm for Training Deep Networks | 4 | 0.70 | 2013 |
| Learning Optimally Sparse Support Vector Machines. | 7 | 0.50 | 2013 |
| Accelerated Mini-Batch Stochastic Dual Coordinate Ascent | 52 | 2.63 | 2013 |
| The error rate of learning halfspaces using Kernel-SVMs | 0 | 0.34 | 2012 |
| Using More Data to Speed-up Training Time | 12 | 0.81 | 2012 |
| Near-Optimal Algorithms for Online Matrix Prediction | 0 | 0.34 | 2012 |
| Proximal Stochastic Dual Coordinate Ascent | 41 | 2.52 | 2012 |
| Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs. | 8 | 0.50 | 2012 |
| Learning Sparse Low-Threshold Linear Classifiers | 0 | 0.34 | 2012 |
