Sotabase

Career

· Professor, Georgia Institute of Technology2025–
· Associate Professor, Georgia Institute of Technology2020–2025
· Assistant Professor, Georgia Institute of Technology2014–2020
· Courant Instructor, New York University2012–2014
· Postdoctoral Researcher, California Institute of Technology2011–2012
· Ph.D. in Control & Dynamical Systems, California Institute of Technology2006–2011
· B.S. in Mathematics and Physics, Tsinghua University2002–2006

Publications (74)

Statistics of dislocation slip avalanches in nanosized single crystals show tuned critical behavior predicted by a simple mean field model.
Physical Review Letters · 2012
192
cited
gDDIM: Generalized denoising diffusion implicit models
International Conference on Learning Representations · 2022
148
cited
Nonintrusive and Structure Preserving Multiscale Integration of Stiff ODEs, SDEs, and Hamiltonian Systems with Hidden Slow Dynamics via Flow Averaging
Multiscale Modeling & simulation · 2009
113
cited
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? - A Neural Tangent Kernel Perspective
Neural Information Processing Systems · 2020
104
cited
Explicit symplectic approximation of nonseparable Hamiltonians: Algorithm and long time performance.
Physical Review E · 2016
99
cited
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
International Conference on Machine Learning · 2021
68
cited
Explicit high-order symplectic integrators for charged particles in general electromagnetic fields
Journal of Computational Physics · 2016
57
cited
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
International Conference on Learning Representations · 2021
50
cited
The Mirror Langevin Algorithm Converges with Vanishing Bias
International Conference on Algorithmic Learning Theory · 2021
45
cited
Evaluation of a wave-vector-frequency-domain method for nonlinear wave propagation.
Journal of the Acoustical Society of America · 2009
44
cited
UNCOVERING CIRCUMBINARY PLANETARY ARCHITECTURAL PROPERTIES FROM SELECTION BIASES
2016
39
cited
Mirror Diffusion Models for Constrained and Watermarked Generation
Neural Information Processing Systems · 2023
35
cited
Sqrt(d) Dimension Dependence of Langevin Monte Carlo
International Conference on Learning Representations · 2021
35
cited
Variational integrators for electric circuits
Journal of Computational Physics · 2011
35
cited
Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function
Neural Information Processing Systems · 2020
30
cited
Space-time phononic crystals with anomalous topological edge states
Physical Review Research · 2019
24
cited
Alternating Mirror Descent for Constrained Min-Max Games
Neural Information Processing Systems · 2022
23
cited
Convex Optimal Uncertainty Quantification
SIAM Journal on Optimization · 2013
21
cited
Deep Momentum Multi-Marginal Schr\"odinger Bridge
2023
20
cited
A Derivative-Free Optimization Method With Application to Functions With Exploding and Vanishing Gradients
IEEE Control Systems Letters · 2021
18
cited
Sotabase
Molei Tao | Researcher Profile | Sotabase | Sotabase