Optimization & Theory

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Partial Differential Equations COLT 2021 AQD: Towards Accurate Quantized Object Detection CVPR 2021 A Quasiconvex Formulation for Radial Cameras CVPR 2021 ARCH: Efficient Adversarial Regularized Training with Caching EMNLP 2021 Architectural Adversarial Robustness: The Case for Deep Pursuit CVPR 2021 A Recipe for Global Convergence Guarantee in Deep Neural Networks AAAI 2021 Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ACL 2021 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks ICML 2021 A Second-Order Approach to Learning With Instance-Dependent Label Noise CVPR 2021 A Sliced Wasserstein Loss for Neural Texture Synthesis CVPR 2021 Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation CVPR 2021 Asynchronous Optimization Methods for Efficient Training of Deep Neural Networks with Guarantees AAAI 2021 Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors ICLR 2021 A Theoretical Analysis of Fine-tuning with Linear Teachers NeurIPS 2021 A Theoretical Analysis of the Repetition Problem in Text Generation AAAI 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 A Trace-restricted Kronecker-Factored Approximation to Natural Gradient AAAI 2021 Attention is not all you need: pure attention loses rank doubly exponentially with depth ICML 2021 AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling CVPR 2021 A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021 A Unified Lottery Ticket Hypothesis for Graph Neural Networks ICML 2021 A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021 AutoDropout: Learning Dropout Patterns to Regularize Deep Networks AAAI 2021 AutoInt: Automatic Integration for Fast Neural Volume Rendering CVPR 2021 AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021