9 papers
Scale Weight Decay and Train Better
Anuj Apte
The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant decoupled weight decay which caus…
Conjectured Bounds for 2-Local Hamiltonians via Token Graphs
Anuj Apte, Ojas Parekh, James Sud
We explain how the maximum energy of the Quantum MaxCut, XY, and EPR Hamiltonians on a graph are related to the spectral radii of the token graphs of . From numerical study,…
Anytime Training with Schedule-Free Spectral Optimization
Anuj Apte, Pranav Deshpande, Niraj Kumar +2
Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Sch…
Quantum Approximate Optimization of Integer Graph Problems and Surpassing Semidefinite Programming for Max-k-Cut
Anuj Apte, Sami Boulebnane, Yuwei Jin +3
Quantum algorithms for binary optimization problems have been the subject of extensive study. However, the application of quantum algorithms to integer optimization problems remain…
Iterative Interpolation Schedules for Quantum Approximate Optimization Algorithm
Anuj Apte, Shree Hari Sureshbabu, Ruslan Shaydulin +5
Quantum Approximate Optimization Algorithm (QAOA) is a promising quantum heuristic with empirical evidence of speedup over classical state-of-the-art for some problems. QAOA uses a…
Regularized Warm-Started Quantum Approximate Optimization and Conditions for Surpassing Classical Solvers on the Max-Cut Problem
Zichang He, Anuj Apte, Brandon Augustino +4
Demonstrating quantum heuristics that outperform strong classical solvers on large-scale optimization remains an open challenge. Here we introduce Regularized Warm-Started QAOA (RW…