Optimization
Enhancing Domain Adaptation through Prompt Gradient Alignment
In particular, prior works often generate pseudo-label for unlabeled images and then train the model on those samples.
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
This class of problems is referred to as the "simple bilevel problem" [
Aligning T arget-A ware Molecule Diffusion Models with Exact Energy Optimization
However, existing models primarily focus on learning the chemical distribution of all drug candidates, which lacks effective steerability on the chemical quality of model generations.
Generative Adversarial Model-Based Optimization via Source Critic Regularization Michael S. Yao
Offline model-based optimization seeks to optimize against a learned surrogate model without querying the true oracle objective function during optimization.
Inexact Augmented Lagrangian Methods for Conic Programs: Quadratic Growth and Linear Convergence
Under the quadratic growth assumption, it is known that the dual iterates and the Karush-Kuhn-Tucker (KKT) residuals of ALMs applied to semidefi-nite programs (SDPs) converge linearly. In contrast, the convergence rate of the primal iterates has remained elusive.
Group-wise oracle-efficient algorithms for online multi-group learning
In contrast to previous work on this learning model, we consider scenarios in which the family of groups is too large to explicitly enumerate, and hence we seek algorithms that only access groups via an optimization oracle.