Cover Image

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tsoy, Nikita, Konstantinov, Nikola
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On Measuring Localization of Shortcuts in Deep Networks
by: Tsoy, Nikita, et al.
Published: (2025)

Implicit Bias of Mirror Flow on Separable Data
by: Pesme, Scott, et al.
Published: (2024)

Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
by: Fan, Chen, et al.
Published: (2025)

Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints
by: Xie, Shengping, et al.
Published: (2026)

Hidden Minima in Two-Layer ReLU Networks
by: Arjevani, Yossi
Published: (2023)

Convex Formulations for Training Two-Layer ReLU Neural Networks
by: Prakhya, Karthik, et al.
Published: (2024)

Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
by: Huo, Dongyan, et al.
Published: (2022)

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
by: Jung, Hyunji, et al.
Published: (2025)

Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
by: Xu, Xianliang, et al.
Published: (2024)

Mean-Field Limits for Two-Layer Neural Networks Trained with Consensus-Based Optimization
by: De Deyn, William, et al.
Published: (2025)

Criteria and Bias of Parameterized Linear Regression under Edge of Stability Regime
by: Zhang, Peiyuan, et al.
Published: (2024)

Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization
by: Kuelbs, Daniel, et al.
Published: (2024)

Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks
by: Yang, Yahong, et al.
Published: (2023)

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
by: Min, Hancheng, et al.
Published: (2025)

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
by: Cai, Yuhang, et al.
Published: (2024)

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
by: Baek, Beomhan, et al.
Published: (2025)

Global Convergence of SGD On Two Layer Neural Nets
by: Gopalani, Pulkit, et al.
Published: (2022)

On the Impact of Performative Risk Minimization for Binary Random Variables
by: Tsoy, Nikita, et al.
Published: (2025)

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
by: Cai, Yuhang, et al.
Published: (2025)

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
by: Gopalani, Pulkit, et al.
Published: (2023)

Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization
by: Iyengar, Garud, et al.
Published: (2023)

Optimization Insights into Deep Diagonal Linear Networks
by: Labarrière, Hippolyte, et al.
Published: (2024)

Two-Timescale Optimization Framework for Sparse-Feedback Linear-Quadratic Optimal Control
by: Feng, Lechen, et al.
Published: (2024)

Symplectic Inductive Bias for Data-Driven Target Reachability in Hamiltonian Systems
by: Ouyang, Zhuo, et al.
Published: (2026)

Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes
by: Meng, Si Yi, et al.
Published: (2024)

Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems
by: Bylinkin, Dmitry, et al.
Published: (2026)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
by: Beneventano, Pierfrancesco, et al.
Published: (2025)

Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
by: Emmanouilidis, Konstantinos, et al.
Published: (2026)

SensLI: Sensitivity-Based Layer Insertion for Neural Networks
by: Kreis, Leonie, et al.
Published: (2023)

Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way
by: Kwon, Jeongyeol, et al.
Published: (2024)

Communication Efficient Federated Learning with Linear Convergence on Heterogeneous Data
by: Liu, Jie, et al.
Published: (2025)

Physics-Informed Neural Networks with Hard Linear Equality Constraints
by: Chen, Hao, et al.
Published: (2024)

Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks
by: Qin, Zhen, et al.
Published: (2023)

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
by: Das, Mohua, et al.
Published: (2026)

Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise
by: Haque, Shaan Ul, et al.
Published: (2023)

Data-Driven Adversarial Online Control for Unknown Linear Systems
by: Liu, Zishun, et al.
Published: (2023)

Interpolation Conditions for Data Consistency and Prediction in Noisy Linear Systems
by: Vanelli, Martina, et al.
Published: (2025)

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
by: Bennouna, Omar, et al.
Published: (2025)

A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning
by: Gokhale, Anand, et al.
Published: (2026)

On subdifferential chain rule of matrix factorization and beyond
by: Guan, Jiewen, et al.
Published: (2024)