Neural Network Optimization

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution NeurIPS 2022 DyRep: Bootstrapping Training With Dynamic Re-Parameterization CVPR 2022 Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks NeurIPS 2022 Early Stopping for Iterative Regularization with General Loss Functions JMLR 2022 Efficient Adversarial Training with Robust Early-Bird Tickets EMNLP 2022 Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking EMNLP 2022 Efficient Tactile Simulation with Differentiability for Robotic Manipulation CoRL 2022 Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators ICLR 2022 Efficient Training of Low-Curvature Neural Networks NeurIPS 2022 Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums ICLR 2022 Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise ICLR 2022 ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation EMNLP 2022 End-to-End Neural Speaker Diarization with an Iterative Refinement of Non-Autoregressive Attention-based Attractors Interspeech 2022 EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models Interspeech 2022 Episodic Policy Gradient Training AAAI 2022 ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions AAAI 2022 Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass ICML 2022 Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits NeurIPS 2022 Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization CVPR 2022 Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing EMNLP 2022 Exact Solutions of a Deep Linear Network NeurIPS 2022 Exploiting Explainable Metrics for Augmented SGD CVPR 2022 Exploring Frequency Adversarial Attacks for Face Forgery Detection CVPR 2022 Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis EMNLP 2022 Exploring the Equivalence of Siamese Self-Supervised Learning via a Unified Gradient Framework CVPR 2022