Related papers: Training independent subnetworks for robust predic…

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

We scrutinize the use of machine learning, based on reservoir computing, to build data-driven effective models of multiscale chaotic systems. We show that, for a wide scale separation, machine learning generates effective models akin to…

This paper takes a new look at Cell-free Massive MIMO (multiple-input multiple-output) through the lens of the dynamic cooperation cluster framework from the Network MIMO literature. The purpose is to identify and address scalability issues…

We develop a generalized inverse optimization framework for fitting the cost vector of a single linear optimization problem given multiple observed decisions. This setting is motivated by ensemble learning, where building consensus from…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks…

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

End-to-end data-driven machine learning (ML) of multiple-input multiple-output (MIMO) systems has been shown to have the potential of exceeding the performance of engineered MIMO transceivers, without any a priori knowledge of…

Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algorithm-hardware co-design approach called MIME. MIME reuses…

In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…

To safely and efficiently solve motion planning problems in multi-agent settings, most approaches attempt to solve a joint optimization that explicitly accounts for the responses triggered in other agents. This often results in solutions…

Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure…

Machine-learning-based parameterizations (i.e. representation of sub-grid processes) of global climate models or turbulent simulations have recently been proposed as a powerful alternative to physical, but empirical, representations,…

This paper proposes a framework for developing forecasting models by streamlining the connections between core components of the developmental process. The proposed framework enables swift and robust integration of new datasets,…

Ensembles of CNN models trained with different seeds (also known as Deep Ensembles) are known to achieve superior performance over a single copy of the CNN. Neural Ensemble Search (NES) can further boost performance by adding architectural…

Highly accurate datasets from numerical or physical experiments are often expensive and time-consuming to acquire, posing a significant challenge for applications that require precise evaluations, potentially across multiple scenarios and…

Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through…