Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

60120179239 · Jun 202019922001200920172026
48 results for contrast maximization

Poly-view contrastive learning improves image representation learning.

problem Learning representations from multiple related views in image data.
method Developed new representation learning objectives for poly-view tasks using information maximization and sufficient statistics.
result Poly-view contrastive models trained for fewer epochs and with smaller batch sizes outperform models trained for more epochs and with larger batch sizes.

Paper connects contrastive learning to MI maximization and establishes robust methods for nonlinear ICA and subspace estimation.

problem Understanding and improving unsupervised representation learning and density ratio estimation.
method The paper connects contrastive learning to MI maximization, establishes new recovery conditions for nonlinear ICA, and proposes a practical outlier-robust method for nonlinear subspace estimation.
result The proposed methods can be seen as maximizing MI, performing nonlinear ICA, or estimating nonlinear subspaces, and are robust to outliers.

GraphCL learns node representations by maximizing similarity between perturbed node features.

problem Learning node representations in graph data without labeled data.
method Contrastive learning of node embeddings using graph neural networks and a loss function.
result Significantly outperforms state-of-the-art in unsupervised node classification benchmarks.

We show that the ball does not maximize the first nonzero Steklov eigenvalue among all contractible domains of fixed boundary volume in Rn\mathbb{R}^n when n3n \geq 3. This is in contrast to the situation when n=2n=2, where a result of Weinstock from 1954 shows that the disk uniquely maximizes the first Steklov eigenval…

2017-11-13abs ↗pdf ↗

Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.

problem Learning high-dimensional representations from multi-modal data.
method Multi-modal contrastive learning with temperature optimization.
result Contrastive learning adapts to intrinsic dimensions of data, not specified dimensions.

New method uses diffusion models to optimize experimental design efficiently.

problem Optimizing experimental design for high-dimensional and complex settings.
method Introduces a pooled posterior distribution and uses diffusion-based samplers for efficient sampling and optimization.
result Extends Bayesian Optimal Experimental Design to practical scenarios.

Model learns image-word associations from captions using contrastive learning.

problem Phrase grounding, associating image regions to caption words.
method Optimizing word-region attention to maximize mutual information, using language model guided word substitutions for negatives.
result Model achieves 76.7% accuracy on Flickr30K Entities benchmark, a 5.7% gain from weak supervision.

New attacks prevent both supervised and contrastive learning from private data.

problem Preventing unauthorized use of private data and commercial datasets.
method Contrastive-like data augmentations in supervised error minimization or maximization frameworks.
result Achieve state-of-the-art worst-case unlearnability across SL and CL algorithms.

Paper proposes a new method for learning compact representations of sequential data.

problem Learning compact representations of sequential data capturing spatio-temporal cues.
method Contrastive representation learning via adversarial optimal transport on the Grassmann manifold.
result Empirical results show competitive performance in human action recognition.

CVRL tackles complex visual observations in reinforcement learning.

problem Complex visual observations in natural environments.
method Contrastive Variational Reinforcement Learning (CVRL) learns a contrastive variational model by maximizing mutual information between latent states and observations.
result CVRL achieves comparable performance with state-of-the-art model-based DRL methods and significantly outperforms them on tasks with complex observations.

Proposes a novel graph representation learning framework using contrastive methods.

problem Graph representation learning for graph-structured data.
method Leverages a contrastive objective at the node level, generating two graph views by corruption and learning node representations by maximizing agreement.
result Consistently outperforms existing state-of-the-art methods on transductive and inductive learning tasks.

Develops a new self-supervised learning method combining contrastive and non-contrastive approaches.

problem Leveraging unlabeled data for representation learning, especially with high variance and low batch sizes.
method Converts a contrastive method (Spectral Contrastive Loss) into a non-contrastive form (MINC loss) to reduce variance and mutual information.
result MINC loss consistently improves upon the Spectral Contrastive loss baseline in learning image representations.

Flaky performance found in GNN SSL on RDBs, leading to worse linear evaluation.

problem Downstream task performances of GNN SSL on RDBs are poor.
method Proposed InfoNode to maximize mutual information between initial and final node representations.
result InfoNode improves GNN SSL performance on RDBs, supporting conjecture of conflict between SSL and GNN message passing.

Unified framework for self-supervised learning via latent distribution matching.

problem Lack of a unifying theoretical framework for diverse SSL methods.
method Casting SSL as latent distribution matching (LDM): maximizing alignment and uniformity.
result Derives a Bayesian filtering model and proves identifiable latent representations.

Abstract. In this paper we prove several rigidity theorems related to and including Lytchak's problem. The focus is on Alexandrov spaces with \curv\geq1, nonempty boundary, and maximal radius \fracπ{2}. We exhibit many such spaces that indicate that this class is remarkably flexible. Nevertheless, we also show that whe…

2018-05-25abs ↗pdf ↗

New mutual information framework improves contrastive learning for vision tasks.

problem Maximizing mutual information for better unsupervised learning representations.
method Reformulated mutual information as a lower bound, introducing new negative sampling strategies.
result Improved representations outperform previous methods in various vision tasks.

The paper studies maximal stretch and Lipschitz maps on negatively curved manifolds.

problem Investigating maximal stretch and Lipschitz maps on negatively curved manifolds.
method Defined maximal stretch for negatively curved manifolds and connected it to best Lipschitz maps.
result The Mather set may not be lifts of geodesic laminations but shares similar features.

In this paper, we study a constrained utility maximization problem following the convex duality approach. After formulating the primal and dual problems, we construct the necessary and sufficient conditions for both the primal and dual problems in terms of FBSDEs plus additional conditions. Such formulation then allows…

2016-12-13abs ↗pdf ↗

While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations fro…

2018-07-10abs ↗pdf ↗

cMIM improves representation learning without positive-pair augmentations.

problem Learning robust representations for diverse tasks.
method Contrastive Mutual Information Machine (cMIM) framework.
result cMIM outperforms MIM and InfoNCE on classification and regression tasks.

We consider learning of submodular functions from data. These functions are important in machine learning and have a wide range of applications, e.g. data summarization, feature selection and active learning. Despite their combinatorial nature, submodular functions can be maximized approximately with strong theoretical…

2018-03-05abs ↗pdf ↗

SinSim improves self-supervised learning by integrating optimal transport into contrastive learning.

problem Lack of explicit regularization in contrastive learning methods leads to suboptimal generalization.
method Integrates Sinkhorn regularization from optimal transport theory into SimCLR.
result SinSim outperforms SimCLR and other self-supervised methods on various datasets.

The main result of this paper is, that for convex billiards in higher dimensions, in contrast with 2D case, for every point on the boundary and for every nn there always exist billiard trajectories developing conjugate points at the nn-th collision with the boundary. We shall explain that this is a consequence of the…

2008-08-23abs ↗pdf ↗

Study optimizes insurance investment to maximize utility across all capital levels.

problem Maximizing expected utility across all capital levels in an insurance company's investment strategy.
method Dynamic Programming Principle and Hamilton-Jacobi-Bellman (HJB) equation to prove existence of optimal strategy.
result Existence of optimal investment strategy proven under certain conditions.

Proposes a framework to reconcile policy learning and profit maximization in CATE estimation.

problem Aligning CATE estimation with profit maximization for optimal customer treatment decisions.
method Optimizes a novel objective function that concentrates learning capacity near the decision boundary, ensuring consistency with the original profit function.
result Consistent CATE estimates can be recovered from existing profit-maximization pipelines, allowing firms to navigate the trade-off between accuracy and profit.

Model identifies causal structure from paired observational and interventional data with unknown soft interventions.

problem Identifying causal structure from observational and interventional data with unknown soft interventions.
method Proposes a scalable causal discovery model that aggregates subset-level PDAGs and applies contrastive cross-regime orientation rules.
result The model asymptotically recovers the identifiable PDAG and can orient additional edges compared to non-contrastive subset-restricted methods.

VJE learns latent representations without contrastive learning, providing probabilistic semantics.

problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.

The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act to maximize the evidence for a biased generative model. Here, we illustrate how i…

2020-02-28abs ↗pdf ↗

Paper proposes a novel graph AL method using contrastive learning.

problem Discovering informative nodes for GNNs with unlabeled data.
method Integrates graph AL with contrastive learning, focusing on homophilous subgraphs.
result Method outperforms state-of-the-arts on five public datasets.