← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Investigating Data Contamination in Modern Benchmarks for Large Language Models NAACL 2024
Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions AAAI 2024
Evaluating Step-by-Step Reasoning through Symbolic Verification NAACL 2024
Neural Model Checking NIPS 2024
Simple Weak Coresets for Non-decomposable Classification Measures AAAI 2024
Dense Associative Memory Through the Lens of Random Features NIPS 2024
A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base NAACL 2024
The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models EMNLP 2024
BotChat: Evaluating LLMs’ Capabilities of Having Multi-Turn Dialogues NAACL 2024
On the Limitations of Fractal Dimension as a Measure of Generalization NIPS 2024
Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models AISTATS 2024
Needle In A Multimodal Haystack NIPS 2024
Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study AAAI 2024
Distributional Properties of Subword Regularization EMNLP 2024
Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees AAAI 2024
GLBench: A Comprehensive Benchmark for Graph with Large Language Models NIPS 2024
Evaluating the design space of diffusion-based generative models NIPS 2024
Analysis of Using Sigmoid Loss for Contrastive Learning AISTATS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
Anisotropy is Not Inherent to Transformers NAACL 2024
What Drives Performance in Multilingual Language Models? NAACL 2024
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond NAACL 2024
MEPSI: An MDL-Based Ensemble Pruning Approach with Structural Information AAAI 2024
On the Misspecification of Linear Assumptions in Synthetic Controls AISTATS 2024
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks NIPS 2024