Imagen de Portada

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Reizinger, Patrik, Balestriero, Randall, Klindt, David, Brendel, Wieland
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
por: Ibrahim, Mark, et al.
Publicado: (2024)

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

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

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

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

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

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
por: Balestriero, Randall, et al.
Publicado: (2025)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
por: Feizi, Aarash, et al.
Publicado: (2024)

InfoNCE: Identifying the Gap Between Theory and Practice
por: Rusak, Evgenia, et al.
Publicado: (2024)

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

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
por: Huang, Hai, et al.
Publicado: (2024)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
por: Otero, Daniel, et al.
Publicado: (2024)

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

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
por: Patel, Niket, et al.
Publicado: (2025)

No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
por: Cai, Daniel, et al.
Publicado: (2025)

SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth
por: Masi, Nick, et al.
Publicado: (2025)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
por: Lu, Wenquan, et al.
Publicado: (2025)

Data Whitening Improves Sparse Autoencoder Learning
por: Saraswatula, Ashwin, et al.
Publicado: (2025)

Fast and Exact Enumeration of Deep Networks Partitions Regions
por: Balestriero, Randall, et al.
Publicado: (2024)

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

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
por: Van Assel, Hugues, et al.
Publicado: (2025)

DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
por: Rodas, Bryan, et al.
Publicado: (2025)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
por: Mueller, Aaron, et al.
Publicado: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
por: Balestriero, Randall, et al.
Publicado: (2024)

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
por: Mayilvahanan, Prasanna, et al.
Publicado: (2025)

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
por: Balestriero, Randall, et al.
Publicado: (2023)

The Fair Language Model Paradox
por: Pinto, Andrea, et al.
Publicado: (2024)

On the Geometry of Deep Learning
por: Balestriero, Randall, et al.
Publicado: (2024)

From superposition to sparse codes: interpretable representations in neural networks
por: Klindt, David, et al.
Publicado: (2025)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
por: Mayilvahanan, Prasanna, et al.
Publicado: (2025)

Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
por: Wijesinghe, Asiri, et al.
Publicado: (2025)

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning
por: Lu, Wenquan, et al.
Publicado: (2026)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
por: Balestriero, Randall, et al.
Publicado: (2025)

Deep Networks Always Grok and Here is Why
por: Humayun, Ahmed Imtiaz, et al.
Publicado: (2024)

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
por: Maes, Lucas, et al.
Publicado: (2026)

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
por: Zhang, Jiaqi, et al.
Publicado: (2025)

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

FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios
por: Moleri, Andrea, et al.
Publicado: (2026)

LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model
por: Salles, Marcel Mateos, et al.
Publicado: (2025)