Related papers: Learning Determinantal Point Processes by Correcti…
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…
Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to…
Recently, self-supervised learning has attracted great attention, since it only requires unlabeled data for model training. Contrastive learning is one popular method for self-supervised learning and has achieved promising empirical…
Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…
Contrastive learning techniques have been widely used in the field of computer vision as a means of augmenting datasets. In this paper, we extend the use of these contrastive learning embeddings to sentiment analysis tasks and demonstrate…
In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are constrained to use a…
In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…
As Large Multimodal Models (LMMs) scale up and reinforcement learning (RL) methods mature, LMMs have made notable progress in complex reasoning and decision making. Yet training still relies on static data and fixed recipes, making it…
Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…
Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…
Given a fixed $n\times d$ matrix $\mathbf{X}$, where $n\gg d$, we study the complexity of sampling from a distribution over all subsets of rows where the probability of a subset is proportional to the squared volume of the parallelepiped…
Distance Metric Learning (DML) has attracted much attention in image processing in recent years. This paper analyzes its impact on supervised fine-tuning language models for Natural Language Processing (NLP) classification tasks under…
In this article, recent results about point processes are used in sampling theory. Precisely, we define and study a new class of sampling designs: determinantal sampling designs. The law of such designs is known, and there exists a simple…
Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…
Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this…
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…
Deceptive path planning (DPP) is the problem of designing a path that hides its true goal from an outside observer. Existing methods for DPP rely on unrealistic assumptions, such as global state observability and perfect model knowledge,…
Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive learning is susceptible to feature suppression, i.e., it may…
Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…
Predictive coding (PC) accounts of perception now form one of the dominant computational theories of the brain, where they prescribe a general algorithm for inference and learning over hierarchical latent probabilistic models. Despite this,…