Image de couverture de livre

When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nielsen, Beatrix M. G., Marconato, Emanuele, Dittadi, Andrea, Gresele, Luigi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Logit Distance Bounds Representational Similarity
par: Nielsen, Beatrix M. G., et autres
Publié: (2026)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
par: Marconato, Emanuele, et autres
Publié: (2024)

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
par: Bortolotti, Samuele, et autres
Publié: (2025)

Relational Linear Properties in Language Models: An Empirical Investigation
par: Valer, Giovanni, et autres
Publié: (2026)

What Representational Similarity Measures Imply about Decodable Information
par: Harvey, Sarah E., et autres
Publié: (2024)

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
par: Joshi, Shruti, et autres
Publié: (2025)

Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
par: Bortolotti, Samuele, et autres
Publié: (2026)

What is causal about causal models and representations?
par: Jørgensen, Frederik Hytting, et autres
Publié: (2025)

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
par: Marconato, Emanuele, et autres
Publié: (2024)

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
par: Vouitsis, Noël, et autres
Publié: (2024)

DiffEnc: Variational Diffusion with a Learned Encoder
par: Nielsen, Beatrix M. G., et autres
Publié: (2023)

Causal Component Analysis
par: Wendong, Liang, et autres
Publié: (2023)

A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
par: Bortolotti, Samuele, et autres
Publié: (2024)

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
par: Marconato, Emanuele, et autres
Publié: (2025)

Identifying Representations for Intervention Extrapolation
par: Saengkyongam, Sorawit, et autres
Publié: (2023)

Exploration Implies Data Augmentation: Reachability and Generalisation in Contextual MDPs
par: Weltevrede, Max, et autres
Publié: (2024)

When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry
par: Korte, Kathrin, et autres
Publié: (2026)

When Does Non-Uniform Replay Matter in Reinforcement Learning?
par: Korniak, Michal, et autres
Publié: (2026)

When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
par: Schäfer, Lukas, et autres
Publié: (2026)

Molecular Graph Representation Learning via Structural Similarity Information
par: Yao, Chengyu, et autres
Publié: (2024)

SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs
par: Amouzouvi, Kossi, et autres
Publié: (2025)

When and How to Canonize: A Generalization Perspective
par: Sverdlov, Yonatan, et autres
Publié: (2026)

When Bias Meets Trainability: Connecting Theories of Initialization
par: Bassi, Alberto, et autres
Publié: (2025)

From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases
par: Tom, Gary, et autres
Publié: (2025)

When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
par: Zhang, Yizhou
Publié: (2025)

Early Detection of Multidrug Resistance Using Multivariate Time Series Analysis and Interpretable Patient-Similarity Representations
par: Escudero-Arnanz, Óscar, et autres
Publié: (2025)

Identifying General Mechanism Shifts in Linear Causal Representations
par: Chen, Tianyu, et autres
Publié: (2024)

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
par: Reizinger, Patrik, et autres
Publié: (2024)

A Distributional Analogue to the Successor Representation
par: Wiltzer, Harley, et autres
Publié: (2024)

When Truthful Representations Flip Under Deceptive Instructions?
par: Long, Xianxuan, et autres
Publié: (2025)

Representation Invariance and Allocation: When Subgroup Balance Matters
par: Alloula, Anissa, et autres
Publié: (2025)

The Triangle of Similarity: A Multi-Faceted Framework for Comparing Neural Network Representations
par: Sirikova, Olha, et autres
Publié: (2026)

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
par: Aguilar, Leonel, et autres
Publié: (2026)

Closed-form merging of parameter-efficient modules for Federated Continual Learning
par: Salami, Riccardo, et autres
Publié: (2024)

Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?
par: Weiss, Eyal
Publié: (2026)

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
par: Kori, Avinash, et autres
Publié: (2024)

Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment
par: von Kügelgen, Julius
Publié: (2024)

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
par: Nielsen, Jacob, et autres
Publié: (2025)

When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion
par: Yin, Kejing, et autres
Publié: (2026)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
par: Zeng, Yifan, et autres
Publié: (2026)