Related papers: An Information-Theoretic Perspective on Variance-I…
A fundamental challenge in robust visual-inertial odometry (VIO) is to dynamically assess the reliability of sensor measurements. This assessment is crucial for properly weighting the contribution of each measurement to the state estimate.…
We consider a class of optimization problems with Cartesian variational inequality (CVI) constraints, where the objective function is convex and the CVI is associated with a monotone mapping and a convex Cartesian product set. This…
Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of…
Automatic speech recognition (ASR) has shown rapid advances in recent years but still degrades significantly in far-field and noisy environments. The recent development of self-supervised learning (SSL) technology can improve the ASR…
We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach…
Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little…
Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data-often scraped from the internet. This data can still be sensitive and empirical…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent findings suggest that RLVR…
Reliable uncertainty quantification is essential for deploying machine learning systems in high-stakes domains. Conformal prediction provides distribution-free coverage guarantees but often produces overly large prediction sets, limiting…
We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency. A variational upper bound allows us to implement this method efficiently. The…
Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…
Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve…
Contrastive self supervised learning(CSSL) usually makes use of the multi-view assumption which states that all relevant information must be shared between all views. The main objective of CSSL is to maximize the mutual information(MI)…
Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stochastic counterparts with respect to the convergence rate,…
Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data. However, as real-world applications continually integrate new content, the high computational and…
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of…
Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved…
In the customary VCG (Vickrey-Clarke-Groves) mechanism truth-telling is a dominant strategy. In this paper we study the sequential VCG mechanism and show that other dominant strategies may then exist. We illustrate how this fact can be used…
We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly…
Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversarial regularization (AdvReg) aims to address this issue via…