Image de couverture de livre

Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nema, Ojasva, Sharma, Kaustubh, Chauhan, Aditya, Pareek, Parikshit
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks
par: Sharma, Kaustubh, et autres
Publié: (2026)

Decoupled-Value Attention for Prior-Data Fitted Networks: GP Inference for Physical Equations
par: Sharma, Kaustubh, et autres
Publié: (2025)

Interpolated-MLPs: Controllable Inductive Bias
par: Wu, Sean, et autres
Publié: (2024)

Bilinear MLPs enable weight-based mechanistic interpretability
par: Pearce, Michael T., et autres
Publié: (2024)

Weight-based Decomposition: A Case for Bilinear MLPs
par: Pearce, Michael T., et autres
Publié: (2024)

IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation
par: Tiwari, Amritanshu, et autres
Publié: (2025)

Data-Efficient Strategies for Probabilistic Voltage Envelopes under Network Contingencies
par: Pareek, Parikshit, et autres
Publié: (2023)

Small LLMs with Expert Blocks Are Good Enough for Hyperparamter Tuning
par: Naphade, Om, et autres
Publié: (2025)

Learning Power Flow with Confidence: A Probabilistic Guarantee Framework for Voltage Risk
par: Pareek, Parikshit, et autres
Publié: (2023)

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
par: Chen, Zihao, et autres
Publié: (2025)

Power Flow Approximations for Multiphase Distribution Networks using Gaussian Processes
par: Glover, Daniel, et autres
Publié: (2025)

Compositional Sparsity as an Inductive Bias for Neural Architecture Design
par: Lin, Hongyu, et autres
Publié: (2026)

Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
par: Pareek, Parikshit, et autres
Publié: (2024)

Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias
par: Seo, Joonwon
Publié: (2026)

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
par: Bencomo, Gianluca, et autres
Publié: (2025)

Dataset Difficulty and the Role of Inductive Bias
par: Kwok, Devin, et autres
Publié: (2024)

Towards Exact Computation of Inductive Bias
par: Boopathy, Akhilan, et autres
Publié: (2024)

Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
par: Kosman, Eitan, et autres
Publié: (2026)

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
par: Yıldırım, Alper
Publié: (2026)

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
par: Wu, Lirong, et autres
Publié: (2024)

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
par: Peleg, Amit, et autres
Publié: (2024)

MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
par: Martell, Marc Boubnovski, et autres
Publié: (2026)

Theoretical Investigation on Inductive Bias of Isolation Forest
par: Zheng, Qin-Cheng, et autres
Publié: (2025)

Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
par: Rahmati, Elnaz, et autres
Publié: (2026)

Explaining Grokking in Transformers through the Lens of Inductive Bias
par: Singh, Jaisidh, et autres
Publié: (2026)

Data Distributional Properties As Inductive Bias for Systematic Generalization
par: del Rio, Felipe, et autres
Publié: (2025)

Graph Classification with GNNs: Optimisation, Representation and Inductive Bias
par: a, P. Krishna Kumar, et autres
Publié: (2024)

Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
par: Liu, Yunhui, et autres
Publié: (2024)

Converting MLPs into Polynomials in Closed Form
par: Belrose, Nora, et autres
Publié: (2025)

Training the Untrainable: Introducing Inductive Bias via Representational Alignment
par: Subramaniam, Vighnesh, et autres
Publié: (2024)

MLPs at the EOC: Spectrum of the NTK
par: Terjék, Dávid, et autres
Publié: (2025)

MLPs at the EOC: Concentration of the NTK
par: Terjék, Dávid, et autres
Publié: (2025)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
par: Wang, Xiangmeng, et autres
Publié: (2026)

Rethinking Inductive Bias in Geographically Neural Network Weighted Regression
par: Chen, Zhenyuan
Publié: (2025)

Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
par: Sankaran, Shyam, et autres
Publié: (2026)

Benchmarking Optimizers for MLPs in Tabular Deep Learning
par: Gorishniy, Yury, et autres
Publié: (2026)

MLPMoE: Zero-Shot Architectural Metamorphosis of Dense LLM MLPs into Static Mixture-of-Experts
par: Novikov, Ivan
Publié: (2025)

Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling
par: Mittal, Daksh, et autres
Publié: (2025)

FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning
par: Agrawal, Pulkit, et autres
Publié: (2025)

Soft Geometric Inductive Bias for Object Centric Dynamics
par: Linander, Hampus, et autres
Publié: (2025)