Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning

• URL: http://arxiv.org/abs/2605.04995v1
• Date: Wed, 06 May 2026 14:53:55 GMT
• Title: Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
• Abstract summary: We consider two settings: an unrestricted regime, where querying and approximation are arbitrary functions, and a realizable regime, where we require these operations to be implemented by ReLU neural networks.<n>In both settings, adaptivity never hinders approximation performance.<n>However, this advantage can change when one passes from the unrestricted regime to the realizable regime.
• Score: 10.839949158755656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We compare in-context learning with fixed queries and agentic learning with adaptive queries for uniform approximation of task families. We consider two settings: an unrestricted regime, where querying and approximation are arbitrary functions, and a realizable regime, where we require these operations to be implemented by ReLU neural networks. In both settings, adaptivity never hinders approximation performance. However, this advantage can change when one passes from the unrestricted regime to the realizable regime. We identify four distinct approximation scenarios, each witnessed by an explicit task family: (a) no advantage of adaptivity; (b) an advantage in the unrestricted regime that persists under ReLU realizability; (c) an advantage that arises only under realizability; and (d) an advantage that disappears under realizability. This demonstrates that representational constraints interact profoundly with the effect of adaptivity.

Related papers

• Resilient Constrained Reinforcement Learning [87.4374430686956]
  We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before study. It is challenging to identify appropriate constraint specifications due to the undefined trade-off between the reward training objective and the constraint satisfaction. We propose a new constrained RL approach that searches for policy and constraint specifications together.
  arXiv  Detail & Related papers  (2023-12-28T18:28:23Z)
• Using Property Elicitation to Understand the Impacts of Fairness Regularizers [0.32634122554914]
  We show that it is not well-understood which regularizers change the minimizer of the loss, and, when the minimizer does change, how it changes. We empirically demonstrate how algorithmic decision-making changes as a function of both data distribution changes and hardness of the constraints.
  arXiv  Detail & Related papers  (2023-09-20T14:20:56Z)
• Resilient Constrained Learning [94.27081585149836]
  This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task. We call this approach resilient constrained learning after the term used to describe ecological systems that adapt to disruptions by modifying their operation.
  arXiv  Detail & Related papers  (2023-06-04T18:14:18Z)
• Adaptive Decision-Making with Constraints and Dependent Losses: Performance Guarantees and Applications to Online and Nonlinear Identification [5.787117733071415]
  We consider adaptive decision-making problems where an agent optimize a cumulative performance objective by repeatedly choosing among a finite set of options. Our algorithm and our analysis is instance dependent, that is, suboptimal choices of the environment are exploited and reflected in our regret bounds. The performance of the resulting algorithms is highlighted in two numerical examples.
  arXiv  Detail & Related papers  (2023-04-06T18:32:26Z)
• Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions [8.881195152638986]
  Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function. We provide guarantees for off-policy function estimation under only realizability, by imposing proper regularization on the marginalized importance sampling objectives.
  arXiv  Detail & Related papers  (2022-10-27T15:34:17Z)
• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [104.19414150171472]
  Attributes skews the current federated learning (FL) frameworks from consistent optimization directions among the clients. We propose disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches. Experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods.
  arXiv  Detail & Related papers  (2022-06-14T13:12:12Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Fair Incentives for Repeated Engagement [0.46040036610482665]
  We study a problem of finding optimal monetary incentive schemes for retention when faced with agents whose participation decisions depend on the incentive they receive. We show that even in the absence of explicit discrimination, policies may unintentionally discriminate between agents of different types by varying the type composition of the system.
  arXiv  Detail & Related papers  (2021-10-28T04:13:53Z)
• Improper Learning with Gradient-based Policy Optimization [62.50997487685586]
  We consider an improper reinforcement learning setting where the learner is given M base controllers for an unknown Markov Decision Process. We propose a gradient-based approach that operates over a class of improper mixtures of the controllers.
  arXiv  Detail & Related papers  (2021-02-16T14:53:55Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.