Search and filter through extracted claims from AI researchers.
Showing 121-140 of 451 claims in topic "infrastructure"
"An adapted time-augmented Poincaré inequality yields an explicit rate that improves upon the contraction rate of the underdamped Langevin dynamics."
"Our iteration complexity bound improves upon the existing work on HFHR algorithms."
GRAPE achieves 5.4x speedup over baselines in black-box adversarial attacks
"in black-box adversarial attacks, it achieves an average 5.4$\times$ speedup over baselines"
"on large language model prompt optimization tasks, it outperforms the second best method by a reduction of 3.8 log-units in the final average regret"
"existing techniques often prioritize the probability of descent over the magnitude of progress. This leads to overly conservative steps that yield negligible improvement, wasting queries on directions that are nearly certain to descend but offer little decrease"
"Theoretical analysis proves that this gradient refinement stage monotonically minimizes local uncertainty and that the progress-aware direction converges to true steepest descent as the posterior sharpens"
GRAPE demonstrates superior query efficiency across high-dimensional tasks
"Empirically, GRAPE demonstrates superior query efficiency across high-dimensional tasks"
"For a polytope given by $n$ inequalities and a convex $L$-Lipschitz potential, this yields warm-start mixing in $\widetilde O((d^{2}+dL^{2}R^{2})\log(w/δ))$ steps for the regularized Lee--Sidford walk."
"For a spectrahedron with $n\times n$ blocks, the log-det walk mixes in $\widetilde O((ψ^\star nd+dL^{2}R^{2})\log(w/δ))$ steps, where $ψ^\star$ measures matrix leverage."
"We analyze exact-metric, Metropolis-adjusted Dikin walks by keeping the proposal determinant and reverse quadratic form together. Their leading uncentered terms cancel in the complete logarithmic acceptance ratio, leaving centered fluctuations that can be controlled with second-order tools."
"We prove that no fixed choice of step size and friction, based only on the curvature bounds and the dimension, achieves this acceleration: total variation mixing time lower bounds for OBABO show that ballistic cold-start mixing fails uniformly over the smooth strongly convex class"
"among fixed-parameter OBABO tunings, the optimal condition-number dependence of cold-start total variation mixing over this class is linear, up to logarithmic factors"
"we prove a complementary upper bound of $O(κ)$ steps, up to logarithmic factors, for a fixed-parameter OBABO tuning"
"A direct Gaussian calculation also rules out fixed-parameter acceleration for the left-endpoint exponential integrator"
"Across a 115-job evidence suite on Potjans-inspired recurrent SNNs and mesh NoCs from 4 x 4 to 6 x 6, plus a 7 x 7 stress case, M-HySMap reduces routed multicast hops by 10.6-19.6% over Activity+QAP and 19.7-41.1% over Edge+QAP."
"Incremental updates accelerate refinement by 4.7-12.7x while matching full recomputation to numerical precision."
"Mapping spiking neural networks (SNNs) onto neuromorphic many-core platforms is often formulated with graph partitioning and pairwise placement costs. That abstraction is convenient, but it does not match the physical communication event: one spike from a source neuron is delivered to a set of postsynaptic destinations, and routes to several destinations can share mesh links."
"Every force is screeching towards centralization."
Today's power grid cannot handle the explosive growth of AI data centers
"Can today's power grid handle the explosive growth of AI data centers? Tesla Alum Drew Baglino, now founder & CEO of Heron Power, doesn't think so."
"scaling compute requires a fundamental overhaul of grid-to-chip infrastructure, not just bigger power plants"
Pipeline data may be stale or degraded.
Last synthesis: 2026-09-20. 8,951 pending.