#Mathematics
Latest news articles tagged with "Mathematics". Follow the timeline of events, related topics, and entities.
Articles (8)
-
🇺🇸 Exactly Computing do-Shapley Values
[USA]
arXiv:2602.07203v1 Announce Type: cross Abstract: Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way o...
Related: #Artificial Intelligence, #Data Science -
🇺🇸 iGRPO: Self-Feedback-Driven LLM Reasoning
[USA]
arXiv:2602.09000v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consisten...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 VERIFY-RL: Verifiable Recursive Decomposition for Reinforcement Learning in Mathematical Reasoning
[USA]
arXiv:2602.07559v1 Announce Type: new Abstract: Training language models to solve complex mathematical problems benefits from curriculum learning progressively training on simpler subproblems. Howeve...
Related: #Artificial Intelligence, #Reinforcement Learning -
🇺🇸 Which Graph Shift Operator? A Spectral Answer to an Empirical Question
[USA]
arXiv:2602.06557v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have established themselves as the leading models for learning on graph-structured data, generally categorized into spat...
Related: #Artificial Intelligence, #Data Science -
🇺🇸 Bayesian Matrix Decomposition and Applications
[USA]
arXiv:2302.11337v4 Announce Type: replace-cross Abstract: The sole aim of this book is to give a self-contained introduction to concepts and mathematical tools in Bayesian matrix decomposition in ord...
Related: #Data Science, #Education -
🇺🇸 Hyperbolic Fine-Tuning for Large Language Models
[USA]
arXiv:2410.04010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across various tasks. However, it remains an open question whether the ...
Related: #Artificial Intelligence, #Computational Linguistics -
🇺🇸 The Condensate Theorem: Transformers are O(n), Not $O(n^2)$
[USA]
arXiv:2602.06317v1 Announce Type: cross Abstract: We present the Condensate Theorem: attention sparsity is a learned topological property, not an architectural constraint. Through empirical analysis ...
Related: #Artificial Intelligence, #Computing Efficiency -
🇺🇸 Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics
[USA]
arXiv:2602.06939v1 Announce Type: cross Abstract: Non-Markovian dynamics are commonly found in real-world environments due to long-range dependencies, partial observability, and memory effects. The B...
Related: #Artificial Intelligence, #Machine Learning