Optimistic Gradient
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Breaking $1/\epsilon$ Barrier in Quantum Zero-Sum Games: Generalizing Metric Subregularity for Spectraplexes
arXiv:2509.21570v2 Announce Type: replace Abstract: Quantum zero-sum games provide a framework for non-local games, quantum interactive proofs, and quantum machine learning, where players optimize a bilinear payoff over quantum states. In contrast to classical bilinear games over polyhedral domains, for which gradient methods achieve linear last-iterate convergence, comparable guarantees over spectraplexes have remained open.
Accelerating Min-Max Optimization via Power-Law Stepsizes
Announce Type: cross Abstract: We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization. It is known that EG with a fixed stepsize achieves a $\Theta(T^{-1/2})$ last-iterate convergence rate, which is slower than the optimal $\mathcal{O}(T^{-1})$ rate attainable by incorporating additional mechanisms such as anchoring. Motivated by recent advances showing that dynamic stepsizes alone can significantly accelerate gradient descent,...
Natural Selection in the Wake of Catastrophe
arXiv:2606.09040v1 Announce Type: cross Abstract: Living organisms, from bacteria to humans, are more likely to survive if their traits enhance fitness. In populations well adapted to their environmental niches, natural selection proceeds via rarely beneficial mutations. But when a catastrophe wipes out niche diversity, sudden adaptation often follows.