Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning

Studies on rodents such as mice have shown the capabilities to adapt their behavior when dealing with changing parameters (``drift'') of the environment even if no information about change is provided (uncertainty) -- a behavior that can be modeled by forgetting mechanisms. Non-stationary Reinforcement Learning (NSRL) deals with adapting state-of-the-art RL methods to deal with changing environments: these however usually require (partially) perfect information about the drift such as ``task IDs'' or ``context''. To mitigate the effects of drift, this work develops \emph{Space-sampled Value Decay} as an explicit forgetting mechanism for value-based deep RL architectures as a simple yet effective approach. In particular we demonstrate and discuss positive effects but also limitations in achieved returns for modifications of Deep Q-networks (DQN) and Soft Actor-Critic (SAC) when evaluated on non-stationary environments.

Provably Reduced Sample Cost in Prior-Guided Hyperparameter Optimization

Large-scale hyperparameter optimization (HPO) in automated machine learning (AutoML) consumes substantial computational resources, raising growing concerns about scalability and energy efficiency. Existing methods use prior information heuristically to accelerate both black-box and multi-fidelity settings, but they lack a characterization of how prior informativeness quantitatively reduces sample complexity. In this work, we provide the first distribution-dependent sample complexity bounds for multi-fidelity HPO with priors through the formal lens of fixed-budget best-arm identification. By modeling priors directly over arm means as configuration performance, we derive explicit, distribution-dependent error bounds that quantify the relationship between priors and evaluation budget. Our analysis shows that informative priors, which concentrate probability mass on near-optimal arms, yield reductions in the number of required evaluations, whereas baseline performance is recovered with uninformative or misleading priors. We conduct proof-of-concept experiments on a synthetic benchmark and on LCBench, a common multi-fidelity HPO benchmark for deep learning, to confirm our theoretical results, achieving up to 90% budget reduction while retaining solution quality. Together, our results provide a principled foundation for prior-guided and compute-efficient green AutoML.

Analysis of Search Heuristics in the Multi-Armed Bandit Setting

We consider the classic Multi-Armed Bandit setting to understand the exploration/exploitation tradeoffs made by different search heuristics. Since many search heuristics work by comparing different options (in evolutionary algorithms called "individuals"; in the Bandit literature called "arms"), we work with the "Dueling Bandits" setting. In each iteration, a comparison between different arms can be made; in the binary stochastic setting, each arm has a fixed winning probability against any other arm. A Condorcet winner is any arm that beats every other arm with a probability strictly higher than $1/2$. We show that evolutionary algorithms are rather bad at identifying the Condorcet winner: Even if the Condorcet winner beats every other arm with a probability $1-p$, the (1+1) EA, in its stationary distribution, chooses the Condorcet winner only with constant probability if $p=Ω(1/n)$. By contrast, we show that a simple EDA (based on the Max-Min Ant System with iteration-best update) will choose the Condorcet winner in its maintained distribution with probability $1-Θ(p)$. As a remedy for the (1+1) EA, we show how repeated duels can significantly boost the probability of the Condorcet winner in the stationary distribution.

FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios

Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories. Often, FL methods rely on pretrained foundation models, introducing unrealistic assumptions. We introduce FederatedFactory, a zero-dependency framework that inverts the unit of federation from discriminative parameters to generative priors. By exchanging generative modules in a single communication round, our architecture supports ex nihilo synthesis of universally class balanced datasets, eliminating gradient conflict and external prior bias entirely. Evaluations across diverse medical imagery benchmarks, including MedMNIST and ISIC2019, demonstrate that our approach recovers centralized upper-bound performance. Under pathological heterogeneity, it lifts baseline accuracy from a collapsed 11.36% to 90.57% on CIFAR-10 and restores ISIC2019 AUROC to 90.57%. Additionally, this framework facilitates exact modular unlearning through the deterministic deletion of specific generative modules.

Modular Memory is the Key to Continual Learning Agents

Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning (IWL), i.e., updating a single model's parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale. We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, charting a practical roadmap toward continually learning agents.

A Practical Guide to Streaming Continual Learning

Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they address different and complementary challenges. While SML focuses on rapid adaptation after changes (concept drifts), CL aims to retain past knowledge when learning new tasks. After a brief introduction to CL and SML, we discuss Streaming Continual Learning (SCL), an emerging paradigm providing a unifying solution to real-world problems, which may require both SML and CL abilities. We claim that SCL can i) connect the CL and SML communities, motivating their work towards the same goal, and ii) foster the design of hybrid approaches that can quickly adapt to new information (as in SML) without forgetting previous knowledge (as in CL). We conclude the paper with a motivating example and a set of experiments, highlighting the need for SCL by showing how CL and SML alone struggle in achieving rapid adaptation and knowledge retention.

Drift Localization using Conformal Predictions

Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization -- determining which samples are affected by the drift -- is essential. While several approaches exist, most rely on local testing schemes, which tend to fail in high-dimensional, low-signal settings. In this work, we consider a fundamentally different approach based on conformal predictions. We discuss and show the shortcomings of common approaches and demonstrate the performance of our approach on state-of-the-art image datasets.

DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models have similarly been applied to combinatorial structure generation, including neural architecture search (NAS). However, neural architectures are directed acyclic graphs (DAGs) where edge direction encodes functional semantics such as data flow-information that existing graph diffusion methods, designed for undirected structures, discard. We propose Directed Graph Policy Optimization (DGPO), which extends reinforcement learning fine-tuning of discrete graph diffusion models to DAGs via topological node ordering and positional encoding. Validated on NAS-Bench-101 and NAS-Bench-201, DGPO matches the benchmark optimum on all three NAS-Bench-201 tasks (91.61%, 73.49%, 46.77%). The central finding is that the model learns transferable structural priors: pretrained on only 7% of the search space, it generates near-oracle architectures after fine-tuning, within 0.32 percentage points of the full-data model and extrapolating 7.3 percentage points beyond its training ceiling. Bidirectional control experiments confirm genuine reward-driven steering, with inverse optimization reaching near random-chance accuracy (9.5%). These results demonstrate that reinforcement learning-steered discrete diffusion, once extended to handle directionality, provides a controllable generative framework for directed combinatorial structures.

The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics

Determining whether neural models internalize physical laws as world models, rather than exploiting statistical shortcuts, remains challenging, especially under out-of-distribution (OOD) shifts. Standard evaluations often test latent capability via downstream adaptation (e.g., fine-tuning or high-capacity probes), but such interventions can change the representations being measured and thus confound what was learned during self-supervised learning (SSL). We propose a non-invasive evaluation protocol, PhyIP. We test whether physical quantities are linearly decodable from frozen representations, motivated by the linear representation hypothesis. Across fluid dynamics and orbital mechanics, we find that when SSL achieves low error, latent structure becomes linearly accessible. PhyIP recovers internal energy and Newtonian inverse-square scaling on OOD tests (e.g., $ρ> 0.90$). In contrast, adaptation-based evaluations can collapse this structure ($ρ\approx 0.05$). These findings suggest that adaptation-based evaluation can obscure latent structures and that low-capacity probes offer a more accurate evaluation of physical world models.

Improving the Plausibility of Pressure Distributions Synthesized from Depth through Generative Modeling

Monitoring contact pressure in hospital beds is essential for preventing pressure ulcers and enabling real-time patient assessment. Current methods can predict pressure maps but often lack physical plausibility, limiting clinical reliability. This work proposes a framework that enhances plausibility via Informed Latent Space (ILS) and Weight Optimization Loss (WOL) with generative modeling to produce high-fidelity, physically consistent pressure estimates. This study also applies diffusion based conditional Brownian Bridge Diffusion Model (BBDM) and proposes training strategy for its latent counterpart Latent Brownian Bridge Diffusion Model (LBBDM) tailored for pressure synthesis in lying postures. Experiment results shows proposed method improves physical plausibility and performance over baselines: BBDM with ILS delivers highly detailed maps at higher computational cost and large inference time, whereas LBBDM provides faster inference with competitive performance. Overall, the approach supports non-invasive, vision-based, real-time patient monitoring in clinical environments.