Copertina

Deriving Decoder-Free Sparse Autoencoders from First Principles

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Oursland, Alan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning 68T07 68T07 (Artificial neural networks and deep learning) 68T07, 62H30 I.2.6; G.3
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Gradient Descent as Implicit EM in Distance-Based Neural Models
di: Oursland, Alan
Pubblicazione: (2025)

Federated Learning via Meta-Variational Dropout
di: Jeon, Insu, et al.
Pubblicazione: (2025)

AI-Driven HSI: Multimodality, Fusion, Challenges, and the Deep Learning Revolution
di: Bhatti, David S., et al.
Pubblicazione: (2025)

IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
di: Jeon, Insu, et al.
Pubblicazione: (2025)

Constant-Target Energy Matching: A Unified Framework for Continuous and Discrete Density Estimation
di: Zeng, Zhijun, et al.
Pubblicazione: (2026)

FairEquityFL -- A Fair and Equitable Client Selection in Federated Learning for Heterogeneous IoV Networks
di: Islam, Fahmida, et al.
Pubblicazione: (2025)

Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
di: Wibbeke, Jelke, et al.
Pubblicazione: (2025)

Graph Neural Networks for Efficient AC Power Flow Prediction in Power Grids
di: Talebi, Seyedamirhossein, et al.
Pubblicazione: (2025)

A Tractography Analysis Framework Using Diffusion Maps to Study Thalamic Connectivity in Traumatic Brain Injury
di: Sharma, Akul, et al.
Pubblicazione: (2025)

Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift
di: Landers, Jonathan R.
Pubblicazione: (2026)

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

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
di: Feng, Xuchen, et al.
Pubblicazione: (2025)

ProactBench: Beyond What The User Asked For
di: Harfi, Sepehr, et al.
Pubblicazione: (2026)

Neural Networks Learn Distance Metrics
di: Oursland, Alan
Pubblicazione: (2025)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
di: Brännvall, Rickard, et al.
Pubblicazione: (2023)

Predicting Traffic Accident Severity with Deep Neural Networks
di: Bibb, Meghan, et al.
Pubblicazione: (2025)

GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
di: Fanale, Raimondo
Pubblicazione: (2026)

A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment
di: Zeng, Minmin
Pubblicazione: (2025)

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

Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment
di: Li, Dai, et al.
Pubblicazione: (2025)

Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection
di: Guo, Dongxin, et al.
Pubblicazione: (2026)

Revisiting Unbiased Implicit Variational Inference
di: Pielok, Tobias, et al.
Pubblicazione: (2025)

Model-Free Local Recalibration of Neural Networks
di: Torres, R., et al.
Pubblicazione: (2024)

Machine Collaboration
di: Liu, Qingfeng, et al.
Pubblicazione: (2021)

Can Agentic AI Match the Performance of Human Data Scientists?
di: Luo, An, et al.
Pubblicazione: (2025)

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
di: Luo, An, et al.
Pubblicazione: (2026)

Neural Variational Dropout Processes
di: Jeon, Insu, et al.
Pubblicazione: (2025)

Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions
di: Shevtekar, Sumit S., et al.
Pubblicazione: (2026)

MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data
di: de Zuazo, Xabier, et al.
Pubblicazione: (2026)

The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
di: Rajput, Vishal
Pubblicazione: (2026)

Robust Probabilistic Load Forecasting for a Single Household: A Comparative Study from SARIMA to Transformers on the REFIT Dataset
di: Manoj, Midhun
Pubblicazione: (2025)

From 'What-is' to 'What-if' in Human-Factor Analysis: A Post-Occupancy Evaluation Case
di: Chen, Xia, et al.
Pubblicazione: (2025)

Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules
di: Dahes, Fariza
Pubblicazione: (2025)

Semi-Implicit Variational Inference via Kernelized Path Gradient Descent
di: Pielok, Tobias, et al.
Pubblicazione: (2025)

Neural Networks for Tamed Milstein Approximation of SDEs with Additive Symmetric Jump Noise Driven by a Poisson Random Measure
di: Ramirez-Gonzalez, Jose-Hermenegildo, et al.
Pubblicazione: (2025)

Causal Direction from Convergence Time: Faster Training in the True Causal Direction
di: Tamim, Abdulrahman
Pubblicazione: (2026)

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis
di: Forest, Florent, et al.
Pubblicazione: (2023)

MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
di: Alagöz, Celal, et al.
Pubblicazione: (2026)

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
di: Luo, An, et al.
Pubblicazione: (2025)

When Are Two RLHF Objectives the Same?
di: Gaikwad, Madhava
Pubblicazione: (2025)