Related papers: Reinforced Borrowing Framework: Leveraging Auxilia…

Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external…

Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn…

Federated learning (FL) enables distributed training with private client data, but its convergence is hindered by system heterogeneity under realistic communication scenarios. Most FL schemes addressing system heterogeneity utilize global…

Data is used widely by service providers as input to inference systems to perform decision making for authorized tasks. The raw data however allows a service provider to infer other sensitive information it has not been authorized for. We…

Global financial crime activity is driving demand for machine learning solutions in fraud prevention. However, prevention systems are commonly serviced to financial institutions in isolation, and few provisions exist for data sharing due to…

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

This paper introduces a novel approach for multi-task regression that connects Kernel Machines (KMs) and Extreme Learning Machines (ELMs) through the exploitation of the Random Fourier Features (RFFs) approximation of the RBF kernel. In…

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing…

Federated recommendation (FR) facilitates collaborative training by aggregating local models from massive devices, enabling client-specific personalization while ensuring privacy. However, we empirically and theoretically demonstrate that…

Adversarial examples causing evasive predictions are widely used to evaluate and improve the robustness of machine learning models. However, current studies focus on supervised learning tasks, relying on the ground-truth data label, a…

We propose a new causal inference framework to learn causal effects from multiple, decentralized data sources in a federated setting. We introduce an adaptive transfer algorithm that learns the similarities among the data sources by…

Nowadays, deep learning methods with large-scale datasets can produce clinically useful models for computer-aided diagnosis. However, the privacy and ethical concerns are increasingly critical, which make it difficult to collect large…

Expanding a lower-dimensional problem to a higher-dimensional space and then projecting back is often beneficial. This article rigorously investigates this perspective in the context of finite mixture models, namely how to improve inference…

Integrating heterogeneous data sources and expert knowledge is essential for overcoming data scarcity and enhancing estimation accuracy. Two main frameworks naturally arise to perform the integration of these multiple sources: sequential…

Federated recommender systems have distinct advantages in terms of privacy protection over traditional recommender systems that are centralized at a data center. However, previous work on federated recommender systems does not fully…

Data analysis of files that are a result of linking records from multiple sources are often affected by linkage errors. Records may be linked incorrectly, or their links may be missed. In consequence, it is essential that such errors are…

Machine learning methods allow us to make recommendations to users in applications across fields including entertainment, dating, and commerce, by exploiting similarities in users' interaction patterns. However, in domains that demand…

Autoregressive models have emerged as a powerful framework for modeling exchangeable sequences - i.i.d. observations when conditioned on some latent factor - enabling direct modeling of uncertainty from missing data (rather than a latent).…

In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can significantly streamline…

Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM)…