Stephan Wojtowytsch

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 28

Top Topics

Ambrosio Tortorelli

Differential Equations

Top Venues

J. Nonlinear Sci.

SIAM J. Math. Anal.

Publications

Xuan Zhang, Jacob Helwig, Yuchao Lin, Yaochen Xie, Cong Fu, Stephan Wojtowytsch, Shuiwang Ji
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations. ICLR (2024)
Stephan Wojtowytsch
Stochastic Gradient Descent with Noise of Machine Learning Type Part II: Continuous Time Analysis. J. Nonlinear Sci. 34 (1) (2024)
Xuan Zhang, Jacob Helwig, Yuchao Lin, Yaochen Xie, Cong Fu, Stephan Wojtowytsch, Shuiwang Ji
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations. CoRR (2024)
Kanan Gupta, Jonathan W. Siegel, Stephan Wojtowytsch
Achieving acceleration despite very noisy gradients. CoRR (2023)
Jiyoung Park, Ian Pelakh, Stephan Wojtowytsch
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias. NeurIPS (2023)
Jacob Helwig, Xuan Zhang, Cong Fu, Jerry Kurtin, Stephan Wojtowytsch, Shuiwang Ji
Group Equivariant Fourier Neural Operators for Partial Differential Equations. CoRR (2023)
Stephan Wojtowytsch
Stochastic Gradient Descent with Noise of Machine Learning Type Part I: Discrete Time Analysis. J. Nonlinear Sci. 33 (3) (2023)
Jiyoung Park, Ian Pelakh, Stephan Wojtowytsch
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias. CoRR (2023)
Jacob Helwig, Xuan Zhang, Cong Fu, Jerry Kurtin, Stephan Wojtowytsch, Shuiwang Ji
Group Equivariant Fourier Neural Operators for Partial Differential Equations. ICML (2023)
Jonathan W. Siegel, Stephan Wojtowytsch
A qualitative difference between gradient flows of convex functions in finite- and infinite-dimensional Hilbert spaces. CoRR (2023)
Stephan Wojtowytsch
Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality. CoRR (2022)
Josiah Park, Stephan Wojtowytsch
Qualitative neural network approximation over R and C: Elementary proofs for analytic and polynomial activation. CoRR (2022)
Weinan E, Stephan Wojtowytsch
Some observations on high-dimensional partial differential equations with Barron data. MSML (2021)
Stephan Wojtowytsch
Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis. CoRR (2021)
Weinan E, Stephan Wojtowytsch
On the emergence of simplex symmetry in the final and penultimate layers of neural network classifiers. MSML (2021)
Irene Fonseca, Janusz Ginster, Stephan Wojtowytsch
On the Motion of Curved Dislocations in Three Dimensions: Simplified Linearized Elasticity. SIAM J. Math. Anal. 53 (2) (2021)
Stephan Wojtowytsch
Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysis. CoRR (2021)
Weinan E, Stephan Wojtowytsch
A priori estimates for classification problems using neural networks. CoRR (2020)
Weinan E, Stephan Wojtowytsch
Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels. CoRR (2020)
Stephan Wojtowytsch, Weinan E
Can Shallow Neural Networks Beat the Curse of Dimensionality? A Mean Field Training Perspective. IEEE Trans. Artif. Intell. 1 (2) (2020)
Stephan Wojtowytsch, Weinan E
Can Shallow Neural Networks Beat the Curse of Dimensionality? A mean field training perspective. CoRR (2020)
Weinan E, Chao Ma, Stephan Wojtowytsch, Lei Wu
Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't. CoRR (2020)
Weinan E, Stephan Wojtowytsch
Representation formulas and pointwise properties for Barron functions. CoRR (2020)
Weinan E, Stephan Wojtowytsch
Some observations on partial differential equations in Barron and multi-layer spaces. CoRR (2020)
Weinan E, Stephan Wojtowytsch
On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics. CoRR (2020)
Weinan E, Stephan Wojtowytsch
On the emergence of tetrahedral symmetry in the final and penultimate layers of neural network classifiers. CoRR (2020)
Stephan Wojtowytsch
On the Convergence of Gradient Descent Training for Two-layer ReLU-networks in the Mean Field Regime. CoRR (2020)
Patrick W. Dondl, Matteo Novaga, Benedikt Wirth, Stephan Wojtowytsch
A Phase-field Approximation of the Perimeter under a Connectedness Constraint. SIAM J. Math. Anal. 51 (5) (2019)