In your Bayesian optimization workflows, optimizing over loss landscapes with degenerate global minima (such as overparameterized neural networks) using a Langevin-dynamics-based surrogate model stratified by the local learning coefficient will yield faster and more stable convergence than standard Langevin algorithms.

Adversarial Debate Score

55% survival rate under critique

Supporting Research Papers

• Bayesian Optimization with Gaussian Processes to Accelerate Stationary Point Searches

  Accelerating the explorations of stationary points on potential energy surfaces building local surrogates spans decades of effort. Done correctly, surrogates reduce required evaluations by an order of...

• Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations

  Balancing convergence speed, generalization capability, and computational efficiency remains a core challenge in deep learning optimization. First-order gradient descent methods, epitomized by stochas...

• Diffeomorphic Optimization

  Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space. Optimizing differentiable objectives on this manifold is challenging: th...

• Convergence of Neural Network Policies for Risk--Reward Optimization

  We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad cla...

• Generalization at the Edge of Stability

  Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this re...

Formal Verification

Source