New #ExpertCertification: FedLOE: Federated Domain Generalization via Locally Overfit Ensemble Ruqi Bai, David I. Inouye openreview.net/forum?id=W4T9s… #federated #generalization #generalize

To truly evaluate AI agents, we need to consider their ability to generalize across tasks and domains. This involves assessing their capacity to learn from diverse experiences and adapt to novel situations. #Generalization

'Boosted Control Functions: Distribution Generalization and Invariance in Confounded Models', by Nicola Gnecco, Jonas Peters, Sebastian Engelke, Niklas Pfister. jmlr.org/papers/v27/24-… #generalization #prediction #causal

A PAC-Bayesian approach to generalization for quantum models. We take steps towards non-uniform and data-dependent bounds for generalization of quantum machine learning models. scirate.com/arxiv/2603.229… In detail, #generalization is a central concept in machine learning theory, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide #nonuniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the worst-case behavior of the entire hypothesis class. To address this limitation, we derive the first #PACBayesian generalization bounds for a broad class of quantum models by analyzing layered circuits composed of general quantum channels, which include dissipative operations such as mid-circuit measurements and feedforward. Through a channel perturbation analysis, we establish non-uniform bounds that depend on the norms of learned parameter matrices; we extend these results to symmetry-constrained equivariant quantum models; and we validate our theoretical framework with numerical experiments. This work provides actionable model design insights and establishes a foundational tool for a more nuanced understanding of generalization in #quantummachinelearning. Warm thanks to the team of @pablones8, Matthias C. Caro, @EliesMiquel, @FJSchreiber, and @charl_bp for this great collaboration.

On the Dynamics & Transferability of Latent Generalization during Memorization Simran Ketha, Venkatakrishnan Ramaswamy. Action editor: William Redman. openreview.net/forum?id=t024Z… #memorization #generalization #dynamics_during_training_dnn

Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out-of-Distribution Generalization openreview.net/forum?id=07fh1… #complexity #ai #generalization

'Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width', by Yunwen Lei, Puyu Wang, Yiming Ying, Ding-Xuan Zhou. jmlr.org/papers/v27/24-… #rademacher #optimal #generalization

The Scaling Laws of Classification Networks: Insights from Adaptive Exact Average Density Approximation openreview.net/forum?id=Y7gwq… #generalization #scaling #networks

FedDID: Discrepancy-Informed Distillation to Target Personalization and Generalization in Federated Learning openreview.net/forum?id=1mbuI… #personalized #generalization #personalization

@timesofindia Hahahha They'll anyways not work for long. They network and then resign. With insights of govt, they begin their own tech startups with added leverages. To satisfy their exam egos, they clear but don't continue for long. #Generalization

@kirarara_ow telling a black person how slavery works to prop your idea on a white man #generalization

Diversity Sampling Regularization for Multi-Domain Generalization Lakpa Tamang, Mohamed Reda Bouadjenek, Sunil Aryal, Richard Dazeley. Action editor: Qi CHEN. openreview.net/forum?id=nXqMt… #diversity #generalization #generalize

🔥 LLMs excel at code, but transferring procedural knowledge to natural language tasks is a tough generalization challenge. 🌊 This paper rigorously assesses LLMs' cross-representation generalization of procedures. #AI #LLM #Generalizationarxiv.org/abs/2602.03542ae

Detecting generalization deficits in large language and reasoning models by using natural variati... Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti, Jenia Jitsev. Action editor: Elahe Arani. openreview.net/forum?id=frA7u… #generalization #ai #reasoni