15 papers
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
Alan Li, Rahul Saha, Anton Xue +4
AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to…
New Lower and Upper Bounds for the Grothendieck Constant
Rahul Saha, Alan Li, Anton Xue +4
We establish new bounds on the Grothendieck constant : \[ \frac{6π}{11} \le K_G \le \fracπ{2\log(1+\sqrt2)} - 10^{-4}. \] Methodologically, our lower bound approach differs fr…
Mask-Aware Policy Gradients for Diffusion Language Models
Haran Raajesh, Kulin Shah, Adam Klivans +1
The paper proposes mask-aware policy gradients for masked diffusion language models, decomposing the policy gradient into token and masking components, which improves performance o…
The Grothendieck Constant is Less Than
Alan Li, Rahul Saha, Anton Xue +4
We prove that the Grothendieck constant . This improves on the work of Braverman, Makarychev, Makarychev, and Naor (2011), who proved…
Iterative Chow Filtering for Learning with Distribution Shift
Gautam Chandrasekaran, Georgios Gkrinias, Adam R. Klivans +2
Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled…
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos +1
Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al.…