Related papers: Multi-TGDR: a regularization method for multi-clas…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…

Multi-dimensional classification (MDC) can be employed in a range of applications where one needs to predict multiple class variables for each given instance. Many existing MDC methods suffer from at least one of inaccuracy, scalability,…

We analyse and explain the increased generalisation performance of iterate averaging using a Gaussian process perturbation model between the true and batch risk surface on the high dimensional quadratic. We derive three phenomena…

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes having a strong correlation with the target attribute are present, the trained model can provide unintended…

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

Multi-class cell detection and counting is an essential task for many pathological diagnoses. Manual counting is tedious and often leads to inter-observer variations among pathologists. While there exist multiple, general-purpose, deep…

Linear Discriminant Analysis (LDA) is a fundamental method for classification. Its simple linear structure facilitates interpretation, and it is naturally suited to multi-class settings. LDA is also closely connected to several classical…

We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm.…

Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small…

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

Controlling the false discovery rate (FDR) is a powerful approach to multiple testing. In many applications, the tested hypotheses have an inherent hierarchical structure. In this paper, we focus on the fixed sequence structure where the…

Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Domain Generalization…

We analyze the sample complexity of full-batch Gradient Descent (GD) in the setup of non-smooth Stochastic Convex Optimization. We show that the generalization error of GD, with common choice of hyper-parameters, can be $\tilde \Theta(d/m +…

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…

Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn…

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a…

Multivariate time-series data in fields like healthcare and industry are informative but challenging due to high dimensionality and lack of labels. Recent self-supervised learning methods excel in learning rich representations without…

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…