Neural Networks can Learn Representations with Gradient Descent. | 0 | 0.34 | 2022 |
Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games | 0 | 0.34 | 2022 |
Optimization-Based Separations for Neural Networks. | 0 | 0.34 | 2022 |
Offline Reinforcement Learning with Realizability and Single-policy Concentrability. | 0 | 0.34 | 2022 |
Impact of Representation Learning in Linear Bandits | 0 | 0.34 | 2021 |
A Theory Of Label Propagation For Subpopulation Shift | 0 | 0.34 | 2021 |
Modeling from Features - a Mean-field Framework for Over-parameterized Deep Neural Networks. | 0 | 0.34 | 2021 |
Near-Optimal Linear Regression Under Distribution Shift | 0 | 0.34 | 2021 |
Shape Matters - Understanding the Implicit Bias of the Noise Covariance. | 0 | 0.34 | 2021 |
On The Theory Of Policy Gradient Methods: Optimality, Approximation, And Distribution Shift | 0 | 0.34 | 2021 |
Few-Shot Learning via Learning the Representation, Provably | 0 | 0.34 | 2021 |
Kernel and Rich Regimes in Overparametrized Models | 0 | 0.34 | 2020 |
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation. | 0 | 0.34 | 2020 |
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks. | 0 | 0.34 | 2020 |
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks | 0 | 0.34 | 2020 |
Beyond Lazy Training for Over-parameterized Tensor Decomposition | 0 | 0.34 | 2020 |
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters | 0 | 0.34 | 2020 |
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot | 0 | 0.34 | 2020 |
SGD Learns One-Layer Networks in WGANs | 0 | 0.34 | 2020 |
Optimal transport mapping via input convex neural networks | 0 | 0.34 | 2020 |
Generalized Leverage Score Sampling for Neural Networks | 0 | 0.34 | 2020 |
Implicit Bias in Deep Linear Classification - Initialization Scale vs Training Accuracy. | 0 | 0.34 | 2020 |
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes | 0 | 0.34 | 2020 |
Towards Understanding Hierarchical Learning: Benefits of Neural Representations | 0 | 0.34 | 2020 |
Agnostic $Q$-learning with Function Approximation in Deterministic Systems - Near-Optimal Bounds on Approximation Error and Sample Complexity. | 0 | 0.34 | 2020 |
Convergence of Adversarial Training in Overparametrized Neural Networks | 1 | 0.35 | 2019 |
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. | 3 | 0.38 | 2019 |
Neural Temporal-Difference Learning Converges to Global Optima. | 4 | 0.39 | 2019 |
Convergence of Adversarial Training in Overparametrized Networks. | 0 | 0.34 | 2019 |
Multi-Turn Beam Search for Neural Dialogue Modeling. | 0 | 0.34 | 2019 |
First-order methods almost always avoid strict saddle points | 7 | 0.55 | 2019 |
Kernel and Deep Regimes in Overparametrized Models. | 0 | 0.34 | 2019 |
Stochastic subgradient method converges on tame functions. | 10 | 0.59 | 2018 |
Characterizing Implicit Bias in Terms of Optimization Geometry. | 9 | 0.49 | 2018 |
Adding One Neuron Can Eliminate All Bad Local Minima. | 4 | 0.38 | 2018 |
On the Margin Theory of Feedforward Neural Networks. | 9 | 0.49 | 2018 |
Solving Non-Convex Non-Concave Min-Max Games Under Polyak-Łojasiewicz Condition. | 2 | 0.36 | 2018 |
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks. | 1 | 0.35 | 2018 |
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport. | 4 | 0.41 | 2018 |
Gradient Descent Finds Global Minima of Deep Neural Networks. | 30 | 0.69 | 2018 |
Implicit Bias of Gradient Descent on Linear Convolutional Networks. | 13 | 0.51 | 2018 |
Convergence of Gradient Descent on Separable Data. | 4 | 0.45 | 2018 |
On the Power of Over-parametrization in Neural Networks with Quadratic Activation. | 20 | 0.63 | 2018 |
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization. | 2 | 0.37 | 2018 |
Provably Correct Automatic Subdifferentiation for Qualified Programs. | 0 | 0.34 | 2018 |
No Spurious Local Minima in a Two Hidden Unit ReLU Network | 1 | 0.35 | 2018 |
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. | 10 | 0.65 | 2018 |
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement. | 11 | 0.50 | 2018 |
Solving Approximate Wasserstein GANs to Stationarity. | 1 | 0.35 | 2018 |
Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement. | 1 | 0.38 | 2017 |