הפקת נתונים מהפצת תפוצה דיסקרטית באמצעות דיפוזיות: תצפיות מבעיות קיפוח תפוצה אקראי

תקציר מקורי באנגליתarXiv:2603.20589v2 Announce Type: replace Abstract: Generating data from discrete distributions is important for a number of application domains including text, tabular data, and genomic data. Several groups have recently used random $k$-satisfiability ($k$-SAT) as a synthetic benchmark for new generative techniques. In this paper, we show that fundamental insights from the theory of random constraint satisfaction problems have observable implications (sometime contradicting intuition) on the behavior of generative techniques on such benchmarks. More precisely, we study the problem of generating a uniformly random solution of a given (random) $k$-SAT or $k$-XORSAT formula. Among other findings, we observe that: $(i)$~Continuous diffusions outperform masked discrete diffusions; $(ii)$~Learn