الباحثون

Leonardo Neves

المنشورات 2

نسخة أولية وصول مفتوح

Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesign 4-bit optimizer-state quantization for AdamW from the perspective of \emph{rounding space}: the coordinate in which a quantizer chooses be …

نسخة أولية وصول مفتوح

From Valid to Useful: Post-Verification Acquisition for Recursive Self-Improving Recommendation

Tonmoy Hasan, Taylor Foust, Shao Tang وآخرون · 2026

Sequential recommenders can generate synthetic interaction sequences and retrain on the augmented corpus in a recursive self-improvement loop. To limit error accumulation, current methods verify each generated sequence remains predictive of the user's real interactions and discard those that drift away from it. Verific …

المؤلفون المشاركون