20 results for “Generalization”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper establishes a large deviation principle for the generalization error of interpolating classifiers in the overparametrized regime.
This paper introduces Neural Expansion, a framework that explains deep neural network generalization through the expansion of directionally-selective ray coverage in the input space.
The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…
The paper introduces Inconsistency-Aware Minimization (IAM), a novel training objective that uses a label-free measure called local inconsistency to improve model generalization, particularly in semi-…
Tianren Zhang, Xiangxin Li, Minghao Xiao, Guanyu Chen +1 more
The paper introduces polynomial representations as a quantitative, distribution-aware metric for measuring model simplicity, demonstrating that the effective degree of this representation is a superio…
The paper introduces a logic-driven framework using a neural certificate function to rigorously evaluate and benchmark the generalization capabilities of reinforcement learning algorithms on unseen ta…
This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…
The paper proposes FedCONST, an approach for federated learning that adaptively modulates update magnitudes to prevent overfitting and promote stronger generalization.
The paper proposes Value-order Decomposition (VOD) to address the challenge of cross-domain generalization in industrial anomaly detection by disentangling and suppressing object-category-, defect-typ…
This paper proposes a bilevel optimization approach to improve generalization of reinforcement learning in unseen test environments using only scalar feedback from validation environments.
Song-Lin Lv, Weiming Wu, Rui Zhu, Zi-Jian Cheng +1 more
This paper introduces OpenAgent, a problem setting for diagnosing the impact of distributional shifts on Large Language Model agents, and proposes Perturbation-Augmented Fine-Tuning as a solution.
The authors show that an explicit information bottleneck in a recurrent neural network is necessary for rotational and out-of-distribution generalization in a time-series prediction task, and that the…
The study assesses the generalization capability of supervised machine learning models for intrusion detection using UNSW-NB15 and TON_IoT, finding a significant performance drop when models are teste…
This paper investigates the use of strategically diverse data in self-training for LLMs, showing that diversity of approaches can matter more than correctness or teacher scale.
This paper demystifies neural networks for classical statisticians by describing networks that approximate linear regression and common customizations.