Related papers: Fully Exploiting Every Real Sample: SuperPixel Sam…
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…
Sub-sequence splitting (SSS) has been demonstrated as an effective approach to mitigate data sparsity in sequential recommendation (SR) by splitting a raw user interaction sequence into multiple sub-sequences. Previous studies have…
The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks. Recently, an increasing awareness has emerged that users should be given more control about how their data is…
Self-supervised learning (SSL) speech models generate meaningful representations of given clips and achieve incredible performance across various downstream tasks. Model extraction attack (MEA) often refers to an adversary stealing the…
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…
Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially…
Deep Neural Networks are powerful tools for understanding complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. Saliency-Guided Training (SGT) methods try to…
Gradient coding is a technique for straggler mitigation in distributed learning. In this paper we design novel gradient codes using tools from classical coding theory, namely, cyclic MDS codes, which compare favorably with existing…
Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that…
Score-based Generative Models (SGMs) is one leading method in generative modeling, renowned for their ability to generate high-quality samples from complex, high-dimensional data distributions. The method enjoys empirical success and is…
Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning…
Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled \emph{with} replacement. In practice, however, sampling \emph{without} replacement is very common, easier to…
Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an…
The 3D Gaussian splatting methods are getting popular. However, they work directly on the signal, leading to a dense representation of the signal. Even with some techniques such as pruning or distillation, the results are still dense. In…
A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…
Spiking neural networks (SNNs) have shown their competence in handling spatial-temporal event-based data with low energy consumption. Similar to conventional artificial neural networks (ANNs), SNNs are also vulnerable to gradient-based…
State space models (SSMs) are a flexible approach to modeling complex time series. However, inference in SSMs is often computationally prohibitive for long time series. Stochastic gradient MCMC (SGMCMC) is a popular method for scalable…
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a…
Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…
The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem. However, this paradigm…