Unverified50% confidenceFactExact time
On every sub-exponential instance, for g(t)=ω(log t) satisfying mild feasibility conditions, the expected pseudo-regret of EL-F is bounded by g(T)∑Δ_i + C_P, where C_P is an instance-dependent constant independent of the time T.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe pseudo-regret of g-Forcing satisfies R(T)=O(g(T)) and R(T)/g(T) converges almost surely to the sum of the suboptimality gaps of all suboptimal arms, but this is an asymptotic statement and does not answer the expected performance and extreme risk under finite T.71% similarUnverifiedThe paper proves that under a finite p-th moment condition (p>1), the joint process (θ_t, m_t) forgets its initial condition at a geometric rate, and a unique stationary causal solution exists.67% similarUnverifiedA high-probability upper bound means that with probability at least 1−δ the regret does not exceed some expression in terms of the number of rounds T, which is stronger than a bound in the expectation sense.66% similarUnverifiedε-prediction is prone to numerical instability at large embedding dimensions, because when α_bar_t approaches zero the scaling factor 1/sqrt(α_bar_t) tends to infinity, amplifying prediction errors.66% similarUnverifiedThe limiting log marginal likelihood derived under the HTMP assumption is a convex function with respect to the heavy-tail degree parameter.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022992API
curl https://kongchang.com/api/v1/knowledge/claims/1022992MCP
get_claim(id=1022992)