Related papers: Improving Minimax Group Fairness in Sequential Rec…

The goal of this paper is to develop distributionally robust optimization (DRO) estimators, specifically for multidimensional Extreme Value Theory (EVT) statistics. EVT supports using semi-parametric models called max-stable distributions…

We consider the penalized distributionally robust optimization (DRO) problem with a closed, convex uncertainty set, a setting that encompasses learning using $f$-DRO and spectral/$L$-risk minimization. We present Drago, a stochastic…

Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the training data is a product of the system being optimised. Recommender systems are a canonical…

Submodular functions have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function $f$. We focus on stochastic functions that are given as an expectation of functions over a…

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Sequential recommendation (SRS) has become the technical foundation in many applications recently, which aims to recommend the next item based on the user's historical interactions. However, sequential recommendation often faces the problem…

Social recommendation system is to predict unobserved user-item rating values by taking advantage of user-user social relation and user-item ratings. However, user/item diversities in social recommendations are not well utilized in the…

Group recommender systems (GRS) are critical in discovering relevant items from a near-infinite inventory based on group preferences rather than individual preferences, like recommending a movie, restaurant, or tourist destination to a…

Sequential recommender systems (SRS) have become the key technology in capturing user's dynamic interests and generating high-quality recommendations. Current state-of-the-art sequential recommender models are typically based on a…

Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids. By capitalizing on a scalable neural network (NN) architecture, one can attain decentralized DER decisions to…

Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward…

This study aims at comparing two sequential recommender systems: Self-Attention based Sequential Recommendation (SASRec), and Beyond Self-Attention based Sequential Recommendation (BSARec) in order to check the improvement frequency…

In this work, we present an algorithmically tractable safe approximation of distributionally robust optimization (DRO) problems that contain univariate indicator functions. The latter appear in different applications, but render the model…

Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative learning, group distributionally robust…

Accounting for the fact that users have different sequential patterns, the main drawback of state-of-the-art recommendation strategies is that a fixed sequence length of user-item interactions is required as input to train the models. This…

Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from source domains. Nonetheless, emerging evidence shows that CDR can inadvertently…

Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however,…

Cross-Domain Sequential Recommendation (CDSR) methods aim to tackle the data sparsity and cold-start problems present in Single-Domain Sequential Recommendation (SDSR). Existing CDSR works design their elaborate structures relying on…

We consider stochastic programs conditional on some covariate information, where the only knowledge of the possible relationship between the uncertain parameters and the covariates is reduced to a finite data sample of their joint…

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to…