Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
org/abs/2310.08566
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Transformers trained to imitate Bayesian posterior Neyman allocations achieve smoothness-adaptive ATE estimation via mixture-of-experts in-context learning.
A Graph Attention Network pretrained solely on synthetic MDPs solves held-out tabular RL benchmarks in context, outperforming UCB-VI and Q-learning online while matching VI-LCB offline.
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
Non-linear transformers enable cross-domain generalization in in-context RL by representing value functions from different domains with shared weights inside a shared RKHS.
citing papers explorer
-
Convergent Stochastic Training of Attention and Understanding LoRA
Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
-
Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
Transformers trained to imitate Bayesian posterior Neyman allocations achieve smoothness-adaptive ATE estimation via mixture-of-experts in-context learning.
-
Reinforcement Learning Foundation Models Should Already Be A Thing
A Graph Attention Network pretrained solely on synthetic MDPs solves held-out tabular RL benchmarks in context, outperforming UCB-VI and Q-learning online while matching VI-LCB offline.
-
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
-
One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
Non-linear transformers enable cross-domain generalization in in-context RL by representing value functions from different domains with shared weights inside a shared RKHS.