In offline reinforcement learning, it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. One class of methods, the policy-regularized method, addresses this problem by constraining the target policy to stay close to the behavior policy. Although several approaches suggest representing the behavior policy as an expressive diffusion model to boost performance, it remains unclear how to regularize the target policy given a diffusion-modeled behavior sampler. In this paper, we propose Diffusion Actor-Critic (DAC) that formulates the Kullback-Leibler (KL) constraint policy iteration as a diffusion noise regression problem, enabling direct representation of target policies as diffusion models. Our approach follows the actor-critic learning paradigm in which we alternatively train a diffusion-modeled target policy and a critic network. The actor training loss includes a soft Q-guidance term from the Q-gradient. The soft Q-guidance is based on the theoretical solution of the KL constraint policy iteration, which prevents the learned policy from taking out-of-distribution actions. We demonstrate that such diffusion-based policy constraint, along with the coupling of the lower confidence bound of the Q-ensemble as value targets, not only preserves the multi-modality of target policies, but also contributes to stable convergence and strong performance in DAC. Our approach is evaluated on D4RL benchmarks and outperforms the state-of-the-art in nearly all environments.

Classification with imbalanced datasets has garnered escalating attention as it is inherent in various applications. In the context of imbalanced tabular data classification, columns may have multiple and skewed distributions, making existing methods fail to properly model this data structure. To address this problem, we propose the Invertible TabMap, a novel framework creatively amalgamating a newly devised self-supervised paradigm named TabMap with a designed invertible network. Different from existing self-supervised learning for tabular data, TabMap maximizes the mutual information between global and specifically designed local structures. These local structures are extracted from specific feature combinations that reveal the distinctive essence between imbalanced classes, and they are robust to permutations of tabular columns. TabMap aims to create a latent space that aligns with these abundant and diverse local structures, from which effective representations are generated for classification. To further mitigate data imbalance to train a better classifier, we formulate an invertible network capable of simultaneously generating minority class samples and selecting high-quality samples. The generation process generates minority class samples in the TabMap latent space by an invertible generator. Subsequently, the selection module operates in the invertible latent space, selecting high-quality samples to train classifiers. Extensive experiments demonstrate that the proposed framework leads to significant improvements in the acquisition and synthesis of imbalance information, and it exhibits state-of-the-art performance for the classification task of imbalanced tabular data compared with other existing alternative methods.

Tabular data is widely utilized in a wide range of real-world applications. The challenge of few-shot learning with tabular data stands as a crucial problem in both industry and academia, due to the high cost or even impossibility of annotating additional samples. However, the inherent heterogeneity of tabular features, combined with the scarcity of labeled data, presents a significant challenge in tabular few-shot classification. In this paper, we propose a novel approach named Diffusion-based Representation with Random Distance matching (D2R2) for tabular few-shot learning. D2R2 leverages the powerful expression ability of diffusion models to extract essential semantic knowledge crucial for denoising process. This semantic knowledge proves beneficial in few-shot downstream tasks. During the training process of our designed diffusion model, we introduce a random distance matching to preserve distance information in the embeddings, thereby improving effectiveness for classification. During the classification stage, we introduce an instance-wise iterative prototype scheme to improve performance by accommodating the multimodality of embeddings and increasing clustering robustness. Our experiments reveal the significant efficacy of D2R2 across various tabular few-shot learning benchmarks, demonstrating its state-of-the-art performance in this field.

Summary Mobile data offloading has already appeared to offer the means of addressing the challenges of limited computing capability and battery life of mobile devices. Most existing code offloading frameworks only consider migrating an application within a single network at a time and failed to fully utilize the energy efficiency mechanism of the latest CPU chips. To tackle these issues, we propose an offloading approach under both a multitasking environment and a heterogeneous network to increase energy and execution efficiency. The offloading problem was formulated as a biobjective optimization problem that aims to save energy and keep a good performance by combining mobile cloud computing with big.LITTLE technology under a heterogeneous network equipped with cellular and WiFi connectivity. By varying the applications and network scenarios, the experimental results show that with offloading a single application using our proposed framework, the data‐intensive application can obviously benefit when the access point density of WiFi reaches 0.0002 unit/m2. Under multiple application scenarios, our proposed framework can increase processing speed by an average of 0.3× over the single application and can save an average of 25% power over the single application.