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

Theory

4,950 papers

Papers per year

Papers

Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022
A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning AAAI 2022
How Many Representatives Do We Need? The Optimal Size of a Congress Voting on Binary Issues AAAI 2022
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks AAAI 2022
Inconsistent Planning: When in Doubt, Toss a Coin! AAAI 2022
Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate AAAI 2022
Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems AAAI 2022
Local and Global Convergence of General Burer-Monteiro Tensor Optimizations AAAI 2022
The King Is Naked: On the Notion of Robustness for Natural Language Processing AAAI 2022
Toward a New Science of Common Sense AAAI 2022
Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs AAAI 2022
Does the Geometry of the Data Control the Geometry of Neural Predictions? (Student Abstract) AAAI 2022
A Simplified Benchmark for Ambiguous Explanations of Knowledge Graph Link Prediction Using Relational Graph Convolutional Networks (Student Abstract) AAAI 2022
Number Theory Meets Linguistics: Modelling Noun Pluralisation Across 1497 Languages Using 2-adic Metrics AACL 2022
Putting WordNet’s Dictionary Examples in the Context of Definition Modelling: An Empirical Analysis AACL 2022
Creative Text-to-Image Generation: Suggestions for a Benchmark AACL 2022
Quantified Reproducibility Assessment of NLP Results ACL 2022
TruthfulQA: Measuring How Models Mimic Human Falsehoods ACL 2022
A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022
Entailment Graph Learning with Textual Entailment and Soft Transitivity ACL 2022
Logic Traps in Evaluating Attribution Scores ACL 2022
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED ACL 2022
Overcoming a Theoretical Limitation of Self-Attention ACL 2022
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions ACL 2022
Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks ACL 2022