Cover Image

InfoNCE: Identifying the Gap Between Theory and Practice

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rusak, Evgenia, Reizinger, Patrik, Juhos, Attila, Bringmann, Oliver, Zimmermann, Roland S., Brendel, Wieland
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

In Search of Forgotten Domain Generalization
by: Mayilvahanan, Prasanna, et al.
Published: (2024)

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
by: Koromilas, Panagiotis, et al.
Published: (2024)

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
by: Mayilvahanan, Prasanna, et al.
Published: (2023)

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
by: Li, Fanfei, et al.
Published: (2025)

InfoNCE Induces Gaussian Distribution
by: Betser, Roy, et al.
Published: (2026)

Low-Pass Filtering Improves Behavioral Alignment of Vision Models
by: Wolff, Max, et al.
Published: (2026)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
by: Zimmermann, Roland S., et al.
Published: (2023)

Cross-Entropy Is All You Need To Invert the Data Generating Process
by: Reizinger, Patrik, et al.
Published: (2024)

Effective pruning of web-scale datasets based on complexity of concept clusters
by: Abbas, Amro, et al.
Published: (2024)

Don't trust your eyes: on the (un)reliability of feature visualizations
by: Geirhos, Robert, et al.
Published: (2023)

Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering
by: Cheng, Ge, et al.
Published: (2025)

$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
by: Lu, Yiwei, et al.
Published: (2024)

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
by: Rajendran, Goutham, et al.
Published: (2023)

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
by: Reizinger, Patrik, et al.
Published: (2024)

InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
by: Wang, Zixu, et al.
Published: (2025)

When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
by: Erol, Melihcan, et al.
Published: (2026)

Generation is Required for Data-Efficient Perception
by: Brady, Jack, et al.
Published: (2025)

Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE
by: Chaudhry, Faris
Published: (2026)

Estimating Treatment Effects with Independent Component Analysis
by: Reizinger, Patrik, et al.
Published: (2025)

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
by: Joshi, Shruti, et al.
Published: (2026)

Interaction Asymmetry: A General Principle for Learning Composable Abstractions
by: Brady, Jack, et al.
Published: (2024)

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
by: Reizinger, Patrik, et al.
Published: (2025)

TraNCE: Transformative Non-linear Concept Explainer for CNNs
by: Akpudo, Ugochukwu Ejike, et al.
Published: (2025)

Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
by: Mészáros, Anna, et al.
Published: (2024)

Provable Compositional Generalization for Object-Centric Learning
by: Wiedemer, Thaddäus, et al.
Published: (2023)

Position: Understanding LLMs Requires More Than Statistical Generalization
by: Reizinger, Patrik, et al.
Published: (2024)

Causality is Key for Interpretability Claims to Generalise
by: Joshi, Shruti, et al.
Published: (2026)

InfoClus: Informative Clustering of High-dimensional Data Embeddings
by: Lai, Fuyin, et al.
Published: (2025)

Reliable Mislabel Detection for Video Capsule Endoscopy Data
by: Werner, Julia, et al.
Published: (2026)

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
by: Zeller, Jana, et al.
Published: (2026)

Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
by: Tian, Hongduan, et al.
Published: (2024)

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
by: Li, Jianxiong, et al.
Published: (2024)

Double InfoGAN for Contrastive Analysis
by: Carton, Florence, et al.
Published: (2024)

Mind the Domain Gap: Measuring the Domain Gap Between Real-World and Synthetic Point Clouds for Automated Driving Development
by: Duc, Nguyen, et al.
Published: (2025)

InfoGNN: End-to-end deep learning on mesh via graph neural networks
by: Gao, Ling, et al.
Published: (2025)

Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
by: Enomoto, Shohei
Published: (2025)

MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
by: Li, Pengyi, et al.
Published: (2025)

Generalization Bounds for Robust Contrastive Learning: From Theory to Practice
by: Tran, Ngoc N., et al.
Published: (2023)

$\texttt{InfoHier}$: Hierarchical Information Extraction via Encoding and Embedding
by: Zhang, Tianru, et al.
Published: (2025)