Cover Image

Task structure and nonlinearity jointly determine learned representational geometry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Alleman, Matteo, Lindsey, Jack W, Fusi, Stefano
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A mathematical theory for understanding when abstract representations emerge in neural networks
by: Wang, Bin, et al.
Published: (2025)

Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
by: Lippl, Samuel, et al.
Published: (2023)

Statistical and structural identifiability in representation learning
by: Nelson, Walter, et al.
Published: (2026)

Evaluating representation learning on the protein structure universe
by: Jamasb, Arian R., et al.
Published: (2024)

Large language models reorganize representational geometry during in-context learning
by: Xiong, Hua-Dong, et al.
Published: (2026)

On the geometry and topology of representations: the manifolds of modular addition
by: Moisescu-Pareja, Gabriela, et al.
Published: (2025)

From Simulation to Enaction: Post-trained language models recognize and react to their own generations
by: G., Asvin, et al.
Published: (2026)

The geometry of BERT
by: Bonino, Matteo, et al.
Published: (2025)

Category learning in deep neural networks: Information content and geometry of internal representations
by: Bonnasse-Gahot, Laurent, et al.
Published: (2025)

DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis
by: Petkov, Hristo, et al.
Published: (2026)

Recent advances in interpretable machine learning using structure-based protein representations
by: Vecchietti, Luiz Felipe, et al.
Published: (2024)

Slot Machines: How LLMs Keep Track of Multiple Entities
by: Bogdan, Paul C., et al.
Published: (2026)

Fubini Study geometry of representation drift in high dimensional data
by: Tozzi, Arturo
Published: (2026)

Biology-informed neural networks learn nonlinear representations from omics data to improve genomic prediction and interpretability
by: Kontolati, Katiana, et al.
Published: (2025)

IGDA: Interactive Graph Discovery through Large Language Model Agents
by: Havrilla, Alex, et al.
Published: (2025)

Transformers learn factored representations
by: Shai, Adam, et al.
Published: (2026)

Decoder ensembling for learned latent geometries
by: Syrota, Stas, et al.
Published: (2024)

Knowledge distillation through geometry-aware representational alignment
by: Bhattarai, Prajjwal, et al.
Published: (2025)

Learning representations of learning representations
by: González-Márquez, Rita, et al.
Published: (2024)

A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
by: Catarau-Cotutiu, Corina, et al.
Published: (2025)

The impact of conformer quality on learned representations of molecular conformer ensembles
by: Adams, Keir, et al.
Published: (2025)

Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error
by: Gross, Markus
Published: (2026)

Causal representation learning from network data
by: Zhang, Jifan, et al.
Published: (2025)

When do complex-valued neural networks help? A study of representation, geometry, and optimization
by: Kumar, Ashutosh
Published: (2026)

Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation
by: Wan, Yue, et al.
Published: (2023)

Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
by: Fioravanti, Stefano, et al.
Published: (2025)

Curriculum reinforcement learning with measurable task representation learning
by: Wen, Yongyan, et al.
Published: (2026)

Continuous latent representations for modeling precipitation with deep learning
by: Radhakrishnan, Gokul, et al.
Published: (2024)

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

Jointly spatial-temporal representation learning for individual trajectories
by: Huang, Fei, et al.
Published: (2023)

Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
by: Guan, Yang, et al.
Published: (2021)

Dynamic Embeddings with Task-Oriented prompting
by: Balloccu, Allmin, et al.
Published: (2024)

Hybrid machine learning based scale bridging framework for permeability prediction of fibrous structures
by: Korolev, Denis, et al.
Published: (2025)

Elements of Conformal Prediction for Statisticians
by: Sesia, Matteo, et al.
Published: (2026)

First-order ANIL provably learns representations despite overparametrization
by: Yüksel, Oğuz Kaan, et al.
Published: (2023)

Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification
by: Wells, Aydin, et al.
Published: (2026)

Model-based learning for joint channel estimationand hybrid MIMO precoding
by: Klaimi, Nay, et al.
Published: (2025)

Sparsity regularization via tree-structured environments for disentangled representations
by: Layne, Elliot, et al.
Published: (2024)

Constrained belief updates explain geometric structures in transformer representations
by: Piotrowski, Mateusz, et al.
Published: (2025)

How can representation dimension dominate structurally pruned LLMs?
by: Xu, Mingxue, et al.
Published: (2025)