OfflineRLisdeemed to be promising [16, 14] as online learning requires the agent to continuously interact with the environment, which howevermaybecostly,time-consuming, orevendangerous.

Infact, modelingmulti-modal 3 k means Continuous action dataset (|A| x a)Clustering into k bins Action offset (1 x a)Continuous action (1 x a)Categorical action bin (1 x k)Continuous action (1 x a)k means encoderk means decoderA.

However, numbers for BCQ and SAC are from our runs for all tasks. These plots show that, in the vast majority of environments, CDC exhibits consistently better performance across different seeds/iterations.

Thelimited datainbatchRLproduces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data.

Reinforcement learning (RL) is typically concerned with estimating stationary policies orsingle-step models, leveraging theMarkovproperty tofactorize problems in time. However, we can also view RL as a generic sequence modeling problem, with the goal being to produce a sequence of actions that leads to a sequence ofhighrewards.

Many fields collect large-scale temporal data through repeated measurements (trials), where each trial is labeled with a set of metadata variables spanning several categories. For example, a trial in a neuroscience study may be linked to a value from category (a): task difficulty, and category (b): animal choice. A critical challenge in time-series analysis is to understand how these labels are encoded within the multi-trial observations, and disentangle the distinct effect of each label entry across categories. Here, we present MILCCI, a novel data-driven method that i) identifies the interpretable components underlying the data, ii) captures cross-trial variability, and iii) integrates label information to understand each category's representation within the data. MILCCI extends a sparse per-trial decomposition that leverages label similarities within each category to enable subtle, label-driven cross-trial adjustments in component compositions and to distinguish the contribution of each category. MILCCI also learns each component's corresponding temporal trace, which evolves over time within each trial and varies flexibly across trials. We demonstrate MILCCI's performance through both synthetic and real-world examples, including voting patterns, online page view trends, and neuronal recordings.

EVs are poised to age like smartphones. For most of its short life, my Tesla Model 3 has aged beautifully. Since I bought the car, in 2019, it has received a number of new features simply by updating its software. My navigation system no longer just directs me to EV chargers along my route--it also shows me, in real time, how many plugs are free. With the push of a button, I can activate "Car Wash Mode," and the Tesla will put itself in neutral and disable the windshield wipers.

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. W e introduce a lightweight defense using tensor decomposition suitable for any pre-trained VLM, requiring no retraining. By decomposing and reconstructing vision encoder representations, it filters adversarial noise while preserving meaning. Experiments with CLIP on COCO and Flickr30K show improved robustness. On Flickr30K, it restores 12.3% performance lost to attacks, raising Recall@1 accuracy from 7.5% to 19.8%. On COCO, it recovers 8.1% performance, improving accuracy from 3.8% to 11.9%. Analysis shows T ensor Train decomposition with low rank (8-32) and low residual strength ( α = 0 . 1 0. 2) is optimal. This method is a practical, plug-and-play solution with minimal overhead for existing VLMs.

Canonical Polyadic (CP) tensor decomposition is a fundamental technique for analyzing high-dimensional tensor data. While the Alternating Least Squares (ALS) algorithm is widely used for computing CP decomposition due to its simplicity and empirical success, its theoretical foundation, particularly regarding statistical optimality and convergence behavior, remain underdeveloped, especially in noisy, non-orthogonal, and higher-rank settings. In this work, we revisit CP tensor decomposition from a statistical perspective and provide a comprehensive theoretical analysis of ALS under a signal-plus-noise model. We establish non-asymptotic, minimax-optimal error bounds for tensors of general order, dimensions, and rank, assuming suitable initialization. To enable such initialization, we propose Tucker-based Approximation with Simultaneous Diagonalization (TASD), a robust method that improves stability and accuracy in noisy regimes. Combined with ALS, TASD yields a statistically consistent estimator. We further analyze the convergence dynamics of ALS, identifying a two-phase pattern-initial quadratic convergence followed by linear refinement. We further show that in the rank-one setting, ALS with an appropriately chosen initialization attains optimal error within just one or two iterations.