Optimization & Theory

Benign Overfitting in Two-layer Convolutional Neural Networks NeurIPS 2022 Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 bert2BERT: Towards Reusable Pretrained Language Models ACL 2022 BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation EMNLP 2022 Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection EMNLP 2022 Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules NeurIPS 2022 Beyond GNNs: An Efficient Architecture for Graph Problems AAAI 2022 Beyond Sub-Gaussian Noises: Sharp Concentration Analysis for Stochastic Gradient Descent JMLR 2022 BiBERT: Accurate Fully Binarized BERT ICLR 2022 BigDL 2.0: Seamless Scaling of AI Pipelines From Laptops to Distributed Cluster CVPR 2022 BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons NeurIPS 2022 Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices Interspeech 2022 BINAS: Bilinear Interpretable Neural Architecture Search ACML 2022 BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models ACL 2022 BiT: Robustly Binarized Multi-distilled Transformer NeurIPS 2022 Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization ICML 2022 Bi-volution: A Static and Dynamic Coupled Filter AAAI 2022 Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution NeurIPS 2022 Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs AAAI 2022 Block-Skim: Efficient Question Answering for Transformer AAAI 2022 BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation NAACL 2022 BLOX: Macro Neural Architecture Search Benchmark and Algorithms NeurIPS 2022 BMCook: A Task-agnostic Compression Toolkit for Big Models EMNLP 2022 BMInf: An Efficient Toolkit for Big Model Inference and Tuning ACL 2022