artificialintelbulletin.com

Tag: cs.LG

  • Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

    Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

    [Submitted on 9 Oct 2026]

    View PDF

    Abstract:Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy. When tasks arrive sequentially, both approaches suffer from catastrophic forgetting. Fine-tuning on a task degrades prior tasks, and steering only shifts forgetting to the shared steering module. We propose Dream to Remember (D2R), which continually steers a frozen generalist policy toward new tasks, while retaining its earlier skills. As the steering module learns a new task, a frozen pretrained world model rehearses prior tasks through imagined rollouts, anchoring the module to its earlier behavior without a replay buffer or new data. When the world model is faithful enough, D2R learns the new task entirely in imagination. Otherwise, it learns the task in the environment while using the world model only to rehearse prior tasks. On CALVIN, D2R improves eight tasks in sequence entirely in imagination, raising average success from 63.7% to 74.8%, while LoRA fine-tuning on the same sequence drops it to 11.7%. With a frozen off-the-shelf generalist policy and world model, $pi_0$ and A2World, D2R learns unseen LIBERO-90 tasks in the environment while keeping $pi_0$’s performance on the LIBERO suites it was fine-tuned on, even though the world model is not accurate enough for policy optimization. Finally, on a real Franka robot, D2R improves three tasks in sequence entirely in imagination while retaining the earlier improvements.

    Submission history

    From: Bahey Tharwat [view email]
    [v1] Fri, 9 Oct 2026 16:28:01 UTC (16,416 KB)

  • STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules

    STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures remains expensive and data-hungry. Existing sparse upcycling methods mainly target Mixture-of-Experts models, where expert homogeneity, sample inefficiency, and system overheads can limit practical scalability. Static sparse memory offers predictable access and token-specific updates that can help address these challenges, but naively integrating it into pretrained computation yields poor returns. In this work, we introduce STAPLE, a recipe built upon STEM for integrating static sparse memory into pretrained models. Whereas STEM replaces FFN up-projections with token-indexed embeddings, STAPLE retains them and adds the embeddings as a residual pathway, preserving pretrained computation while learning complementary token-specific information in a scalable manner. On OLMo-2 1B, STAPLE improves over continued dense training by 4.27 points on HumanEval, 2.80 on MBPP, 2.27 on GSM8K, and 1.65 on DROP. Average performance increases with static capacity, and improvements persist on the larger OLMo-2 7B backbone. STAPLE also outperforms static sparse baselines such as STEM and an Engram-style model, and achieves a higher average score than an MoE upcycling baseline while decoding 2x faster with less than half its GPU model memory and measured GPU energy per token in our throughput-oriented decoding evaluation. Importantly, despite introducing billions of parameters late in training, our host-offloaded implementation keeps generation throughput within 1.5% and training throughput within 3% of the dense baseline, while caching only the ~5% most frequent embeddings on GPU. These results show that static sparse memory can provide a sample-efficient, scalable, and sustainable path for expanding pretrained models without sparse pretraining from scratch.

    Submission history

    From: Rana Sadhukhan [view email]
    [v1] Thu, 8 Oct 2026 18:21:17 UTC (864 KB)

  • Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate

    Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Compression schemes provide a general framework for deriving data-dependent risk bounds for learning algorithms. For learning rules based on preferent compression, existing results upper-bound the risk in terms of a sample-dependent complexity $boldsymbol{k}$, defined as the cardinality of the compression augmented by the training examples on which the reconstructed hypothesis is inappropriate. These results, however, yield a margin of order $O(sqrt{ln N/N})$ above $boldsymbol{k}/N$. In this paper, we establish that the logarithmic factor is not intrinsic. We prove that, for every fixed confidence level $1-delta$, the risk is bounded with probability at least $1-delta$ by $$ frac{boldsymbol{k}}{N} + Oleft(frac{1}{sqrt{N}}right), $$ uniformly over all possible values of $boldsymbol{k}$. Thus, risk estimates for learning algorithms based on preferent compression attain the same law-of-large-numbers rate as the empirical estimate of the probability of a fixed event. We also show that the leading term $boldsymbol{k}/N$ is necessary and investigate its relation to the empirical risk. In particular, we identify regimes in which the empirical risk retains the $O(1/sqrt{N})$ convergence rate, as well as regimes in which it converges more slowly or ceases to be consistent, while the complexity-based estimator preserves the $O(1/sqrt{N})$ rate.

    Submission history

    From: Simone Garatti [view email]
    [v1] Fri, 9 Oct 2026 11:44:43 UTC (24 KB)

  • Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring

    Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Modern machine learning models are typically trained on data assumed to be representative of the predictive tasks the model will face in the future, but practical datasets violate this assumption. We focus on outcome-dependent truncation in which an observation appears in the training data depending on its label. Our work connects two largely distinct literatures: efficient learning under truncation and survival analysis. Existing methods for truncated survival analysis do not characterize the optimization landscape and instead rely on iterative procedures such as expectation maximization. We address this gap and prove that Cox regression can be efficiently learned under truncated and right-censored data using first-order optimization when the baseline hazard is known (despite nonconvexity). In contrast, when the baseline hazard is learned jointly, we construct identifiable and correctly specified models whose negative log-likelihood contains strict suboptimal local minima. On experiments with four survival datasets, we show that accounting for truncation reduces the prediction bias induced by naive Cox regression and extends to neural networks. We also show orders of magnitude speedups compared to standard expectation maximization.

    Submission history

    From: Itai Zilberstein [view email]
    [v1] Thu, 8 Oct 2026 13:32:56 UTC (301 KB)

  • How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?

    How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results about the approximation quality are surprisingly thin. Taking an empirical risk minimization perspective, we decompose the deployment error of PFNs into prior, context, and amortization error, and measure the latter against a reference PPD under a realistic prior. Results show that PFNs generally recover the targeted PPD very well. Nevertheless, we find that parts of the residual amortization error persist, especially in textit{rare} settings under the prior pretraining distribution, even when scaling the model size, which manifests in disagreement between independently pretrained PFNs and leaves uncertainty about the predictor at inference time. As a remedy, we study multiple types of Bayesian model averages and find that these can consistently reduce this uncertainty and improve predictions up to full-size TabICLv2 models.

    Submission history

    From: Manuel Hülskamp [view email]
    [v1] Fri, 9 Oct 2026 15:49:24 UTC (237 KB)

  • A Critical Look at Power Sampling when Test Time Sharpening LLMs

    A Critical Look at Power Sampling when Test Time Sharpening LLMs

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Reinforcement learning with verifiable rewards (RLVR) has substantially improved LLM reasoning, yet growing evidence suggests it mainly performs distribution sharpening: concentrating probability mass on reasoning paths the base model already produces. Recent work therefore seeks RLVR’s gains without needing reward signals, by sampling from the power distribution $pi_alpha propto pi_{text{base}}^alpha$ via Markov chain Monte Carlo or sequential Monte Carlo. We show that these samplers fail to converge to $pi_alpha$ under realistic compute budgets, and that their gains are largely recreated via simple Best-of-$N$ with appropriate grading . This suggests they succeed by selecting high-probability sequences, not by approximating $pi_alpha$, raising a natural question: is the power distribution itself a worthwhile target? We test this hypothesis directly by fine-tuning the base model to match $pi_alpha$, sidestepping sampler convergence issues entirely. Despite approximating the target far more faithfully than existing samplers, this strategy yields gains that are noisy and specific to certain models and sampling tasks. Together, our results suggest that the value of power sampling lies not in faithfully targeting $pi_alpha$, but in the simpler goal of extracting sequences the base model already deems likely.

    Submission history

    From: Abiel Malkani Talwar [view email]
    [v1] Fri, 9 Oct 2026 14:29:28 UTC (235 KB)

  • Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning

    Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning

    [Submitted on 16 May 2025 (v1), last revised 9 Oct 2026 (this version, v4)]

    View PDF HTML (experimental)

    Abstract:Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model converges to an incorrect stationary point potentially far from the pursued optimum. Despite its critical impact, the joint effect of communication and computation heterogeneity has remained largely unexplored, due to the intrinsic complexity of their interaction. In this paper, we reveal the fundamentally distinct mechanisms through which heterogeneous communication and computation drive inconsistency in FL. To the best of our knowledge, this is the first unified theoretical analysis of general heterogeneous FL, offering a principled understanding of how these two forms of heterogeneity jointly distort the optimization trajectory under arbitrary choices of local solvers. Motivated by these insights, we propose Federated Heterogeneity-Aware Client Sampling, FedACS, a universal method to eliminate all types of objective inconsistency. We theoretically prove that FedACS converges to the correct optimum at a rate of $O(1/sqrt{R})$, even in dynamic heterogeneous environments. Extensive experiments across multiple datasets show that FedACS outperforms state-of-the-art and category-specific baselines by 4.3%-36%, while reducing communication costs by 22%-89% and computation loads by 14%-105%, respectively.

    Submission history

    From: Shudi Weng [view email]
    [v1] Fri, 16 May 2025 14:31:36 UTC (1,124 KB)
    [v2] Mon, 16 Feb 2026 06:46:40 UTC (585 KB)
    [v3] Sun, 22 Feb 2026 05:58:59 UTC (580 KB)
    [v4] Fri, 9 Oct 2026 01:27:04 UTC (1,377 KB)

  • Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

    Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new recordings but risk catastrophic forgetting of previously learned financial speech patterns. Adapting Whisper-small from a general-domain speech corpus to the Earnings22 benchmark reveals the opposite: all evaluated methods exhibit improvement on held-out financial speech from the same domain during adaptation rather than forgetting. This task complementarity makes regularization counterproductive. Nevertheless, when regularization is warranted, a layer-wise mini-Kronecker-Factored Approximate Curvature (mini-KFAC) approximation seems to achieve lower word error rates (WERs) and more stable optimization than standard diagonal Elastic Weight Consolidation (EWC). The results suggest that task complementarity should be assessed before applying continual learning constraints, and prefer mini-KFAC EWC over diagonal EWC when needed.

    Submission history

    From: Homayoon Beigi [view email]
    [v1] Fri, 9 Oct 2026 11:34:13 UTC (1,103 KB)

  • Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)

    Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)

    [Submitted on 20 Jul 2026 (v1), last revised 9 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:This is an invited commentary on the Psychometrika focus article “Fairness Issues and Evaluation in Psychometrics and AI/ML: What Can We Learn from Each Field?” by Ying Cheng (2026, doi:https://doi.org/10.1017/psy.2026.10110). Cheng offers a systematic comparison between long-standing test fairness and modern algorithmic fairness. Her mapping of the entire testing workflow onto the AI/ML fairness paradigm, rather than only the final selection stage, is a crucial contribution to interdisciplinary fairness research. This commentary extends her discussion by examining two conceptual issues: the distinction between equality and equity, and the role of causality in fairness research. The focus article and this commentary point to directions for future fairness research across the psychometrics and AI/ML communities.

    Submission history

    From: Youmi Suk [view email]
    [v1] Mon, 20 Jul 2026 08:30:06 UTC (14 KB)
    [v2] Fri, 9 Oct 2026 12:26:26 UTC (14 KB)

  • Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems

    Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Boundary-value problems for the Laplace equation develop singular behaviour near corners, edges and junctions that smooth approximators resolve poorly. We combine holomorphic neural networks with singular functions derived from the local geometry and boundary conditions. The representation is harmonic by construction, so no interior residual is needed: the network fits the smooth remainder from boundary data alone, and the enrichment terms capture the singular behaviour. Singular exponents are trainable, so the construction also applies when the local expansion is not known in advance. We extend the approach to three dimensions using independent networks evaluated along complex null directions. The enriched model is the most accurate tested method on every problem. Its margin is several orders of magnitude where the enrichment captures the singularity exactly, and a factor of about 1.7-2.1 over the next-best method on a CdZnTe radiation detector with many singular sites, in both two and three dimensions.

    Submission history

    From: Alejandro Valverde Mahou [view email]
    [v1] Thu, 8 Oct 2026 14:48:38 UTC (1,890 KB)