Hugging Face Trending Papers
Next-token functional estimation
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Sep 18
Next-token functional estimation
The paper introduces a leave‑a‑window‑out estimator for next‑token functionals, such as the surprise probability and test error, in sequences of random variables. By deleting a window of length τ after each index, the estimator generalizes leave‑one‑out and achieves parametric error decay for stationary β‑mixing processes that admit a Marton coupling. The authors provide both upper bounds and a minimax lower bound for the surprise probability, and demonstrate through simulations that their method outperforms traditional baselines on Markov, moving‑average, and autoregressive processes.
arXiv Machine Learning
Aug 27
Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules
arXiv:2608. 25551v1 Announce Type: new Abstract: Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively by inspecting the evolving trajectory.
arXiv Machine Learning
Aug 10
Stochastic Autoregressive Learning
arXiv:2608. 07224v1 Announce Type: new Abstract: Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic autoregressive learning.
arXiv Machine Learning
Aug 17
Online Inference in Distributional Temporal-Difference Learning
arXiv:2608. 14408v1 Announce Type: cross Abstract: We study online statistical inference for functionals of the return distribution under a fixed policy.
arXiv Machine Learning
Sep 10
Mixing Makes Markovian Contexts Cheap for Linear Bandits
The paper extends the idea that contexts are cheap for linear bandits from i.i.d. settings to Markovian context processes. By assuming uniform geometric ergodicity, the authors construct a stationary surrogate action set and use a delayed‑update scheme to mitigate bias from nonstationary conditional context distributions. They provide a phased algorithm for unknown stationary distributions and achieve high‑probability regret bounds comparable to standard linear bandit oracles in fast‑mixing regimes, with empirical validation showing gains over LinUCB.
arXiv Machine Learning
Jun 4
Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
arXiv:2602. 05657v2 Announce Type: replace Abstract: The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm.