Copertina

SplInterp: Improving our Understanding and Training of Sparse Autoencoders

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Budd, Jeremy, Ideami, Javier, Rynne, Benjamin Macdowall, Duggar, Keith, Balestriero, Randall
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence 68T07, 65D07
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Accuracy and stability of Artificial Neural Networks for HP-Splines frequency parameter selection
di: Bruni, Vittoria, et al.
Pubblicazione: (2026)

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks
di: Appella, Simone, et al.
Pubblicazione: (2024)

FastLRNR and Sparse Physics Informed Backpropagation
di: Cho, Woojin, et al.
Pubblicazione: (2024)

STM Image Analysis using Autoencoders
di: Binev, Peter, et al.
Pubblicazione: (2025)

Graph-Instructed Neural Networks for Sparse Grid-Based Discontinuity Detectors
di: Della Santa, Francesco, et al.
Pubblicazione: (2024)

A Generalization Bound for a Family of Implicit Networks
di: Fung, Samy Wu, et al.
Pubblicazione: (2024)

An algorithmic approach to direct spline products: procedures and computational aspects
di: Patrizi, Francesco, et al.
Pubblicazione: (2026)

Efficient Subdivision of Bézier Curves/Surfaces via Blossoms
di: Vlachkova, Krassimira
Pubblicazione: (2026)

Sprecher Networks: A Parameter-Efficient Kolmogorov-Arnold Architecture
di: Hägg, Christian, et al.
Pubblicazione: (2025)

Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
di: Cho, Woojin, et al.
Pubblicazione: (2025)

A C^s-smooth mixed degree and regularity isogeometric spline space over planar multi-patch domains
di: Kapl, Mario, et al.
Pubblicazione: (2024)

Rational complex Bezier curves
di: Canton, A., et al.
Pubblicazione: (2025)

Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions
di: He, Juncai, et al.
Pubblicazione: (2023)

Regularity and tailored regularization of Deep Neural Networks, with application to parametric PDEs in uncertainty quantification
di: Keller, Alexander, et al.
Pubblicazione: (2025)

Deep Learning Based on Randomized Quasi-Monte Carlo Method for Solving Linear Kolmogorov Partial Differential Equation
di: Xiao, Jichang, et al.
Pubblicazione: (2023)

Autoencoders in Function Space
di: Bunker, Justin, et al.
Pubblicazione: (2024)

Greedy feature selection: Classifier-dependent feature selection via greedy methods
di: Camattari, Fabiana, et al.
Pubblicazione: (2024)

Near-optimal learning of Banach-valued, high-dimensional functions via deep neural networks
di: Adcock, Ben, et al.
Pubblicazione: (2022)

How Can Deep Neural Networks Fail Even With Global Optima?
di: Guan, Qingguang
Pubblicazione: (2024)

Learning Geometric-Aware Quadrature Rules for Functional Minimization
di: Smaragdakis, Costas
Pubblicazione: (2025)

Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization
di: Boche, Holger, et al.
Pubblicazione: (2024)

Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids
di: Cho, Sung Woong, et al.
Pubblicazione: (2024)

Solving Approximation Tasks with Greedy Deep Kernel Methods
di: Klink, Marian, et al.
Pubblicazione: (2025)

Capturing Shock Waves by Relaxation Neural Networks
di: Zhou, Nan, et al.
Pubblicazione: (2024)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
di: Yamchote, Phaphontee, et al.
Pubblicazione: (2025)

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
di: Pavlov, Gorgi
Pubblicazione: (2026)

Deriving Decoder-Free Sparse Autoencoders from First Principles
di: Oursland, Alan
Pubblicazione: (2026)

S$^2$GPT-PINNs: Sparse and Small models for PDEs
di: Ji, Yajie, et al.
Pubblicazione: (2025)

Marrying Compressed Sensing and Deep Signal Separation
di: Hickok, Truman, et al.
Pubblicazione: (2024)

Securing the Dark Matter: A Semantic-Enhanced Neuro-Symbolic Framework for Supply Chain Analysis of Opaque Industrial Software
di: Ning, Bowei, et al.
Pubblicazione: (2026)

Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
di: Gonon, Lukas, et al.
Pubblicazione: (2023)

Deep asymptotic expansion method for solving singularly perturbed time-dependent reaction-advection-diffusion equations
di: Zhu, Qiao, et al.
Pubblicazione: (2025)

Learning to Integrate
di: Ernst, Oliver G., et al.
Pubblicazione: (2025)

Estimating the Distribution of Parameters in Differential Equations with Repeated Cross-Sectional Data
di: Jo, Hyeontae, et al.
Pubblicazione: (2024)

On the algorithmic construction of deep ReLU networks
di: Huybrechs, Daan
Pubblicazione: (2025)

Certified and accurate computation of function space norms of deep neural networks
di: Gründler, Johannes, et al.
Pubblicazione: (2026)

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
di: Antil, Harbir, et al.
Pubblicazione: (2025)

A neuron-wise subspace correction method for the finite neuron method
di: Park, Jongho, et al.
Pubblicazione: (2022)

A Paired Autoencoder Framework for Inverse Problems via Bayes Risk Minimization
di: Hart, Emma, et al.
Pubblicazione: (2025)

EGPT-PINN: Entropy-enhanced Generative Pre-Trained Physics Informed Neural Networks for parameterized nonlinear conservation laws
di: Ji, Yajie, et al.
Pubblicazione: (2025)