Neural Network Optimization

CAT: Customized Adversarial Training for Improved Robustness IJCAI 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 Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss AAAI 2022 Controllable Dynamic Multi-Task Architectures CVPR 2022 Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training AAAI 2022 Data Selection Curriculum for Neural Machine Translation EMNLP 2022 Delving Into the Estimation Shift of Batch Normalization in a Network CVPR 2022 Detached Error Feedback for Distributed SGD with Random Sparsification ICML 2022 DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design Interspeech 2022 Differentiable hierarchical and surrogate gradient search for spiking neural networks NeurIPS 2022 Does the Geometry of the Data Control the Geometry of Neural Predictions? (Student Abstract) AAAI 2022 Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation NAACL 2022 Doubly Sparse Asynchronous Learning for Stochastic Composite Optimization IJCAI 2022 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 Efficient Hyper-parameter Search for Knowledge Graph Embedding ACL 2022 Explain My Surprise: Learning Efficient Long-Term Memory by predicting uncertain outcomes NeurIPS 2022 Exploiting Explainable Metrics for Augmented SGD CVPR 2022 Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study NeurIPS 2022 EZNAS: Evolving Zero-Cost Proxies For Neural Architecture Scoring NeurIPS 2022 Federated Learning With Position-Aware Neurons CVPR 2022 Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs AAAI 2022 Forget-free Continual Learning with Winning Subnetworks ICML 2022 Fractional Adaptive Linear Units AAAI 2022