We study the design of computationally efficient online learning algorithms under smoothed analysis. In this setting, at every step an adversary generates a sample from an adaptively chosen distribution whose density is upper bounded by 1/ times the uniform density. Given access to an offline optimization (ERM) oracle, we give the first computationally efficient online algorithms whose sublinear regret depends only on the pseudo/VC dimension dof the class and the smoothness parameter .

The long-awaited V4 is more efficient and a win for Chinese chipmakers. On Friday, Chinese AI firm DeepSeek released a preview of V4, its long-awaited new flagship model. Notably, the model can process much longer prompts than its last generation, thanks to a new design that helps it handle large amounts of text more efficiently. Like DeepSeek's previous models, V4 is open source, meaning it is available for anyone to download, use, and modify. V4 marks DeepSeek's most significant release since R1, the reasoning model it launched in January 2025. R1, which was trained on limited computing resources, stunned the global AI industry with its strong performance and efficiency, turning DeepSeek from a little-known research team into China's best-known AI company almost overnight.

Machine learning models can frequently produce systematic errors on critical subsets (or slices) of data that share common attributes. Discovering and explaining such model bugs is crucial for reliable model deployment. However, existing bug discovery and interpretation methods usually involve heavy human intervention and annotation, which can be cumbersome and have low bug coverage. In this paper, we propose HiBug, an automated framework for interpretable model debugging. Our approach utilizes large pre-trained models, such as chatGPT, to suggest human-understandable attributes that are related to the targeted computer vision tasks. By leveraging pre-trained vision-language models, we can efficiently identify common visual attributes of underperforming data slices using humanunderstandable terms. This enables us to uncover rare cases in the training data, identify spurious correlations in the model, and use the interpretable debug results to select or generate new training data for model improvement. Experimental results demonstrate the efficacy of the HiBug framework. Code is available at: https://github.com/cure-lab/HiBug.

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL), and its applications in continuous control tasks have recently attracted increasing attention. In this work, we investigate the convergence theory of policy gradient (PG) methods for learning the linear risk-sensitive and robust controller. In particular, we develop PG methods that can be implemented in a derivative-free fashion by sampling system trajectories, and establish both global convergence and sample complexity results in the solutions of two fundamental settings in risk-sensitive and robust control: the finite-horizon linear exponential quadratic Gaussian, and the finite-horizon linear-quadratic disturbance attenuation problems. As a by-product, our results also provide the first sample complexity for the global convergence of PG methods on solving zero-sum linear-quadratic dynamic games, a nonconvex-nonconcave minimax optimization problem that serves as a baseline setting in multi-agent reinforcement learning (MARL) with continuous spaces. One feature of our algorithms is that during the learning phase, a certain level of robustness/risk-sensitivity of the controller is preserved, which we termed as the implicit regularization property, and is an essential requirement in safety-critical control systems.

The5 existing nuclei segmentation benchmarks either worked on 2D only or annotated6 a small number of 3D cells, perhaps due to the high cost of 3D annotation for7 large-scale data. To fulfill the critical need, we constructed NIS3D, a 3D, high8 cell density, large-volume, and completely annotated Nuclei Image Segmentation9 benchmark, assisted by our newly designed semi-automatic annotation software.10 NIS3D provides more than 22,000 cells across multiple most-used species in this11 area. Each cell is labeled by three independent annotators, so we can measure the12 variability of each annotation. A confidence score is computed for each cell, allow-13 ing more nuanced testing and performance comparison. A comprehensive review14 on the methods of segmenting 3D dense nuclei was conducted. The benchmark was15 used to evaluate the performance of several selected state-of-the-art segmentation16 algorithms. The best of current methods is still far away from human-level accuracy,17 corroborating the necessity of generating such a benchmark. The testing results18 also demonstrated the strength and weakness of each method and pointed out the19 directions of further methodological development.

Policy makers often need to estimate the long-term effects of newly-developed treatments, while only having historical data of older treatment options. We propose a surrogate-based approach using a long-term dataset where only past treatments were administered and a short-term dataset where novel treatments have been administered.

Out of the rich family of generalized linear bandits, perhaps the most well studied ones are logistic bandits that are used in problems with binary rewards: for instance, when the learner aims to maximize the profit over a user that can select one of two possible outcomes (e.g., 'click' vs'no-click'). Despite remarkable recent progress and improved algorithms for logistic bandits, existing works do not address practical situations where the number of outcomes that can be selected by the user is larger than two (e.g., 'click', 'show me later', 'never show again', 'no click'). In this paper, we study such an extension. We use multinomial logit (MNL) to model the probability of each one of K+1 2possible outcomes (+1 stands for the'not click' outcome): we assume that for a learner's action xt, the user selects one of K +1 2outcomes, say outcome i, with a MNL probabilistic model with corresponding unknown parameter θ i. Each outcome i is also associated with a revenue parameter ρi and the goal is to maximize the expected revenue. For this problem, we present MNL-UCB, an upper confidence bound (UCB)-based algorithm, that achieves regret O(dK T) with small dependency on problemdependent constants that can otherwise be arbitrarily large and lead to loose regret bounds. We present numerical simulations that corroborate our theoretical results.