Neural Network Optimization

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks ICLR 2022 Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022 Implicit Differentiation for Fast Hyperparameter Selection in Non-Smooth Convex Learning JMLR 2022 Implicit Gradient Alignment in Distributed and Federated Learning AAAI 2022 Implicitly Regularized RL with Implicit Q-values AISTATS 2022 Implicit Parameter-free Online Learning with Truncated Linear Models ALT 2022 Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NeurIPS 2022 Implicit Regularization with Polynomial Growth in Deep Tensor Factorization ICML 2022 Improving Deliberation by Text-Only and Semi-Supervised Training Interspeech 2022 Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging EMNLP 2022 Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment Interspeech 2022 Improving Neural Ordinary Differential Equations with Nesterov's Accelerated Gradient Method NeurIPS 2022 Improving Rare Word Recognition with LM-aware MWER Training Interspeech 2022 Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models EMNLP 2022 Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping EMNLP 2022 Improving Transformers with Probabilistic Attention Keys ICML 2022 Improving Transformer with an Admixture of Attention Heads NeurIPS 2022 In Defense of the Unitary Scalarization for Deep Multi-Task Learning NeurIPS 2022 Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets ALT 2022 Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits L4DC 2022 Instability and Local Minima in GAN Training with Kernel Discriminators NeurIPS 2022 Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations NeurIPS 2022 Introspective Learning : A Two-Stage approach for Inference in Neural Networks NeurIPS 2022 Invertible Monotone Operators for Normalizing Flows NeurIPS 2022 Is Importance Weighting Incompatible with Interpolating Classifiers? ICLR 2022