conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4,950 papers

Papers per year

Papers

Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021
The Low-Dimensional Linear Geometry of Contextualized Word Representations CONLL 2021
On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective CVPR 2021
Understanding the Behaviour of Contrastive Loss CVPR 2021
Relevance-CAM: Your Model Already Knows Where To Look CVPR 2021
Universal Spectral Adversarial Attacks for Deformable Shapes CVPR 2021
The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021
Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021
Neural Response Interpretation Through the Lens of Critical Pathways CVPR 2021
Transformer Interpretability Beyond Attention Visualization CVPR 2021
Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks CVPR 2021
Shape From Sky: Polarimetric Normal Recovery Under the Sky CVPR 2021
Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification? CVPR 2021
Hilbert Sinkhorn Divergence for Optimal Transport CVPR 2021
Understanding Failures of Deep Networks via Robust Feature Extraction CVPR 2021
A Functional Approach to Rotation Equivariant Non-Linearities for Tensor Field Networks. CVPR 2021
Disambiguatory Signals are Stronger in Word-initial Positions EACL 2021
Searching for Search Errors in Neural Morphological Inflection EACL 2021
How Good (really) are Grammatical Error Correction Systems? EACL 2021
Measuring and Improving Faithfulness of Attention in Neural Machine Translation EACL 2021
On Robustness of Neural Semantic Parsers EACL 2021
Do we read what we hear? Modeling orthographic influences on spoken word recognition EACL 2021
The Great Misalignment Problem in Human Evaluation of NLP Methods EACL 2021
Artificial Text Detection via Examining the Topology of Attention Maps EMNLP 2021
Debiasing Methods in Natural Language Understanding Make Bias More Accessible EMNLP 2021