Neural Network Optimization

Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators NeurIPS 2022 BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models ACL 2022 Boosting the Certified Robustness of L-infinity Distance Nets ICLR 2022 Boundary Smoothing for Named Entity Recognition ACL 2022 Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis ICML 2022 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 Certified Neural Network Watermarks with Randomized Smoothing ICML 2022 Channel Pruning via Lookahead Search Guided Reinforcement Learning WACV 2022 Chaotic Dynamics are Intrinsic to Neural Network Training with SGD NeurIPS 2022 Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent NeurIPS 2022 Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling AACL 2022 CHEX: CHannel EXploration for CNN Model Compression CVPR 2022 Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers CVPR 2022 Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks NeurIPS 2022 Composable Sparse Fine-Tuning for Cross-Lingual Transfer ACL 2022 Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation ACL 2022 Continual Learning for Natural Language Generations with Transformer Calibration CoNLL 2022 Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems ICML 2022 Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning CVPR 2022 Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum L4DC 2022 Convergence beyond the over-parameterized regime using Rayleigh quotients NeurIPS 2022 Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime ICML 2022 Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022 Convolutional and Residual Networks Provably Contain Lottery Tickets ICML 2022 Convolution of Convolution: Let Kernels Spatially Collaborate CVPR 2022