Dimitris Oikonomou, Nicolas Loizou · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29192 · open-access PDF
Sharpness-Aware Minimization (SAM) telah menetapkan dirinya sebagai metode yang digunakan secara luas untuk melatih jaringan saraf dalam. Terlepas dari popularitasnya, jaminan konvergensi yang ada untuk metode SAM-tipe membutuhkan kelancaran, asumsi yang membatasi. Kondisi kelancaran umum baru-baru ini diusulkan dalam analisis metode gradient tetapi tetap tidak dijelajahi untuk SAM. Untuk menganalisis efek gangguan SAM di bawah kelancaran generalis, kita menggunakan distorsi gradient relatif untuk mengukur bagaimana arah kesadaran ketajaman beralih dari gradient asli. Di bawah $(L_0,L_1) $-smoothness, kita sho
Machine translation (Meta M2M100); the English original follows.
Sharpness-Aware Minimization (SAM) has established itself as a widely used method for training deep neural networks. Despite its popularity, existing convergence guarantees for SAM-type methods require smoothness, a restrictive assumption. Generalized smoothness conditions have recently been proposed in the analysis of gradient methods but remain underexplored for SAM. To analyze the effect of SAM's perturbation under generalized smoothness, we use relative gradient distortion to quantify how the sharpness-aware direction departs from the original gradient. Under $(L_0,L_1)$-smoothness, we sho
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29192, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange