Copertina

Sparsity regularization via tree-structured environments for disentangled representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Layne, Elliot, Hartford, Jason, Lachapelle, Sébastien, Blanchette, Mathieu, Sridhar, Dhanya
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
di: Joshi, Shruti, et al.
Pubblicazione: (2025)

On the Identifiability of Latent Action Policies
di: Lachapelle, Sébastien
Pubblicazione: (2025)

Causal Representation Learning in Temporal Data via Single-Parent Decoding
di: Brouillard, Philippe, et al.
Pubblicazione: (2024)

PhyloGFN: Phylogenetic inference with generative flow networks
di: Zhou, Mingyang, et al.
Pubblicazione: (2023)

A Sparsity Principle for Partially Observable Causal Representation Learning
di: Xu, Danru, et al.
Pubblicazione: (2024)

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
di: Fawkes, Jake, et al.
Pubblicazione: (2026)

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
di: Xu, Danru, et al.
Pubblicazione: (2026)

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
di: Lachapelle, Sébastien, et al.
Pubblicazione: (2024)

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
di: Morin, Sacha, et al.
Pubblicazione: (2026)

General Causal Imputation via Synthetic Interventions
di: Jiralerspong, Marco, et al.
Pubblicazione: (2024)

IndiSeek learns information-guided disentangled representations
di: Gui, Yu, et al.
Pubblicazione: (2025)

Superposition disentanglement of neural representations reveals hidden alignment
di: Longon, André, et al.
Pubblicazione: (2025)

LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?
di: Gupta, Rushil, et al.
Pubblicazione: (2025)

Identifiable Deep Generative Models via Sparse Decoding
di: Moran, Gemma E., et al.
Pubblicazione: (2021)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
di: Marconato, Emanuele, et al.
Pubblicazione: (2024)

Efficient Biological Data Acquisition through Inference Set Design
di: Neporozhnii, Ihor, et al.
Pubblicazione: (2024)

Demystifying amortized causal discovery with transformers
di: Montagna, Francesco, et al.
Pubblicazione: (2024)

Inference-Time Compute Scaling For Flow Matching
di: Stecklov, Adam, et al.
Pubblicazione: (2025)

Propensity Score Alignment of Unpaired Multimodal Data
di: Xi, Johnny, et al.
Pubblicazione: (2024)

Targeted Sequential Indirect Experiment Design
di: Ailer, Elisabeth, et al.
Pubblicazione: (2024)

Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
di: Gutheil, Julian, et al.
Pubblicazione: (2026)

Variational decomposition autoencoding improves disentanglement of latent representations
di: Ziogas, Ioannis, et al.
Pubblicazione: (2026)

In-Context Learning Can Re-learn Forbidden Tasks
di: Xhonneux, Sophie, et al.
Pubblicazione: (2024)

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

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

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
di: Scimeca, Luca, et al.
Pubblicazione: (2025)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
di: Jiralerspong, Thomas, et al.
Pubblicazione: (2025)

Transferring disentangled representations: bridging the gap between synthetic and real images
di: Dapueto, Jacopo, et al.
Pubblicazione: (2024)

UNSAT Solver Synthesis via Monte Carlo Forest Search
di: Cameron, Chris, et al.
Pubblicazione: (2022)

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

A hierarchy tree data structure for behavior-based user segment representation
di: Liu, Yang, et al.
Pubblicazione: (2025)

Uncovering hidden geometry in Transformers via disentangling position and context
di: Song, Jiajun, et al.
Pubblicazione: (2023)

Automated Discovery of Pairwise Interactions from Unstructured Data
di: Zuheng, et al.
Pubblicazione: (2024)

Evaluating Interventional Reasoning Capabilities of Large Language Models
di: Kasetty, Tejas, et al.
Pubblicazione: (2024)

OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation
di: Ozaydin, Baran, et al.
Pubblicazione: (2024)

Spectrum: Targeted Training on Signal to Noise Ratio
di: Hartford, Eric, et al.
Pubblicazione: (2024)

The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
di: Brouillard, Philippe, et al.
Pubblicazione: (2024)

Does learning the right latent variables necessarily improve in-context learning?
di: Mittal, Sarthak, et al.
Pubblicazione: (2024)

Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective
di: Gagnon, Leo, et al.
Pubblicazione: (2025)

Multi-View Causal Representation Learning with Partial Observability
di: Yao, Dingling, et al.
Pubblicazione: (2023)