Unverified50% confidenceFactExact time
IAFTRL (information-acquisition follow-the-regularized-leader) is claimed by the paper to be the first linear bandit algorithm that achieves both adversarial-optimal (~O(√T) regret) and stochastic instance-dependent optimal (~O(C* log T) regret) performance within a pure FTRL framework.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIAFTRL's analysis combines the stability of FTRL with the instance-dependent lower bound of information acquisition, providing a new tool for subsequent research.66% similarUnverifiedIAST通过在应用内部植入代理结合SAST和DAST的优势，能在运行时精确定位漏洞的代码位置57% similarUnverifiedWhen overlap is poor, the choice of truncation bound should be actively evaluated, and the results of both AIPW and TMLE should be reported rather than choosing only one.57% similarUnverifiedThe authors released the versioned Hallucinated-Tools Benchmark (HTB) to enable cross-submission comparison of resolver solutions.55% similarUnverifiedZY-S1 takes Sapient AI's HRM-Text-1B (a PrefixLM architecture) as its base and performs 1000 steps of supervised fine-tuning (SFT), plus 120 steps of error-correction training.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1128907API
curl https://kongchang.com/api/v1/knowledge/claims/1128907MCP
get_claim(id=1128907)