Optimization

An Adaptive Policy to Employ Sharpness-Aware Minimization ICLR 2023 Anchor Sampling for Federated Learning with Partial Client Participation ICML 2023 A Neural State-Space Modeling Approach to Efficient Speech Separation Interspeech 2023 A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution ICLR 2023 An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization JMLR 2023 An Inverse Scaling Law for CLIP Training NeurIPS 2023 An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization NeurIPS 2023 A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates ICML 2023 Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning ICML 2023 AutoGraph: Optimizing DNN Computation Graph for Parallel GPU Kernel Execution AAAI 2023 AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks AAAI 2023 Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger NeurIPS 2023 Automatic Exploration of Optimal Data Processing Operations for Sound Data Augmentation Using Improved Differentiable Automatic Data Augmentation Interspeech 2023 Automatic Tuning of Loss Trade-offs without Hyper-parameter Search in End-to-End Zero-Shot Speech Synthesis Interspeech 2023 Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity ICML 2023 A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. ICLR 2023 Best-k Search Algorithm for Neural Text Generation ACL 2023 Beta Diffusion NeurIPS 2023 Better Together: Jointly Optimizing ML Collective Scheduling and Execution Planning using SYNDICATE NSDI 2023 Beyond In-Domain Scenarios: Robust Density-Aware Calibration ICML 2023 Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD COLT 2023 Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training ACL 2023 Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training NeurIPS 2023 Bit Allocation using Optimization ICML 2023 Blank Collapse: Compressing CTC Emission for the Faster Decoding Interspeech 2023