← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

On Monotonic Linear Interpolation of Neural Network Parameters ICML 2021
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions ICML 2021
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks ICML 2021
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information ICML 2021
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021
PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data ICML 2021
Implicit Regularization in Tensor Factorization ICML 2021
UnICORNN: A recurrent model for learning very long time dependencies ICML 2021
Momentum Residual Neural Networks ICML 2021
Towards Understanding Learning in Neural Networks with Linear Teachers ICML 2021
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models ICML 2021
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks ICML 2021
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021
Elementary superexpressive activations ICML 2021
Exponentially Many Local Minima in Quantum Neural Networks ICML 2021
On Smoother Attributions using Neural Stochastic Differential Equations IJCAI 2021
Modeling Trajectories with Neural Ordinary Differential Equations IJCAI 2021
DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis IJCAI 2021
Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs IJCAI 2021
Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs IJCAI 2021
Optimal Transport for Deep Generative Models: State of the Art and Research Challenges IJCAI 2021
Relating Adversarially Robust Generalization to Flat Minima ICCV 2021