Broadening the study of quantum optimization algorithms from binary to $k$-element alphabets has been shown to open new avenues for potential quantum advantage. A quantum advantage claim for approximate optimization requires showing that, under the same assumptions, an efficient quantum algorithm provably achieves a be...
Anuj Apte, Abid Khan, E. Farhi et al.· 2 citations
Decoded Quantum Interferometry (DQI) reduces optimization problems with two-variable constraints to decoding cycle codes. For one such problem, namely MaxCut, prior work showed that DQI achieves a nontrivial satisfaction fraction guarantee only on linear-girth graphs, for which MaxCut is classically easy. However, thes...
Anuj Apte, Shouvanik Chakrabarti, An-Di Gu et al.· 1 citation
SF-NorMuon, a schedule-free spectral optimizer that closes the performance gap with tuned AdamW baselines, makes horizon-free optimization more practical, taking a step towards truly open-ended, continual learning.
It is proved that this scaled weight decay preserves the asymptotic stationarity guarantees of the corresponding unregularized methods for both stochastic gradient descent and the non-Euclidean spectral optimizer Muon, thereby avoiding the additional asymptotic bias introduced by constant decoupled weight decay.
Anuj Apte· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
