![We develop a new method for proving a weak functional inequality by first proving it for a sufficiently regular sequence of distributions approximating the stochastic localization (SL) process, and then transferring it to the desired distribution via regularity of the SL process and conductance arguments. We use this strategy to prove a weak Poincaré inequality (WPI) holds for the Gibbs measure of the Sherrington-Kirkpatrick model when β< ¹⁄₂. A prior result of the authors [arXiv:2605.03718, 2026] proves the ASL process for the Sherrington-Kirkpatrick model satisfies the required regularity conditions. A consequence of the WPI is that a much simpler algorithm – Glauber dynamics with a warm-start – efficiently samples the Gibbs measure of the SK model at β< ¹⁄₂. This is a significant structural step towards resolution of the conjecture that Glauber dynamics mixes fast in the replica-symmetric regime for the Sherrington-Kirkpatrick model [arXiv:2504.20539, Open-Problem 15, 2025].](https://pbs.twimg.com/media/HM2SG_KXwAA4hkz.png?name=small&format=webp)
ALT We develop a new method for proving a weak functional inequality by first proving it for a sufficiently regular sequence of distributions approximating the stochastic localization (SL) process, and then transferring it to the desired distribution via regularity of the SL process and conductance arguments. We use this strategy to prove a weak Poincaré inequality (WPI) holds for the Gibbs measure of the Sherrington-Kirkpatrick model when β< ¹⁄₂. A prior result of the authors [arXiv:2605.03718, 2026] proves the ASL process for the Sherrington-Kirkpatrick model satisfies the required regularity conditions. A consequence of the WPI is that a much simpler algorithm – Glauber dynamics with a warm-start – efficiently samples the Gibbs measure of the SK model at β< ¹⁄₂. This is a significant structural step towards resolution of the conjecture that Glauber dynamics mixes fast in the replica-symmetric regime for the Sherrington-Kirkpatrick model [arXiv:2504.20539, Open-Problem 15, 2025].
![Let φ_N be the planar discrete Gaussian free field in [-2N,2N]²∩ℤ², with zero boundary condition imposed by killing the associated simple random walk on exit. We consider the least height H_N at which the two-sided level set {|φ_N|≤ a} contains a nearest-neighbor left–right crossing of [-N,N]²∩ℤ². We prove that (H_N)N≥₁ is tight, uniformly over all box sizes. More precisely, for every a≥0 and N≥1, Φ(-a√(2/log2)) ≤ℙ(H_N>a) ≤4exp{{-2}⁻²⁹a²/log(2+a)}, where Φ is the standard normal distribution function. The upper bound yields uniform polynomial moments and a uniform exponential moment of H_N²/log(2+H_N). For the upper bound, we compare a marked loop-soup exploration with a graph in which independent site variables open incoming edges. We then estimate connections in a massive field using two auxiliary vertices and bound the Gaussian remainder when the mass is removed. The lower bound uses a Gaussian translation inequality and a square-shell estimate for the Dirichlet energy, without usin](https://pbs.twimg.com/media/HXXfVhUXwAAUkRm.png?name=small&format=webp)
ALT Let φ_N be the planar discrete Gaussian free field in [-2N,2N]²∩ℤ², with zero boundary condition imposed by killing the associated simple random walk on exit. We consider the least height H_N at which the two-sided level set {|φ_N|≤ a} contains a nearest-neighbor left–right crossing of [-N,N]²∩ℤ². We prove that (H_N)N≥₁ is tight, uniformly over all box sizes. More precisely, for every a≥0 and N≥1, Φ(-a√(2/log2)) ≤ℙ(H_N>a) ≤4exp{{-2}⁻²⁹a²/log(2+a)}, where Φ is the standard normal distribution function. The upper bound yields uniform polynomial moments and a uniform exponential moment of H_N²/log(2+H_N). For the upper bound, we compare a marked loop-soup exploration with a graph in which independent site variables open incoming edges. We then estimate connections in a massive field using two auxiliary vertices and bound the Gaussian remainder when the mass is removed. The lower bound uses a Gaussian translation inequality and a square-shell estimate for the Dirichlet energy, without usin

ALT We establish sublinear bounds for the internal diameter of External Diffusion Limited Aggregation (DLA) clusters on random planar maps. We develop two conditional DLA growth results for deterministic planar maps: the weaker condition yielding sublinear growth for DLA, and the stronger yielding polynomially sublinear growth for DLA. We then verify the strong assumption a.s. for the γ-mated CRT maps, and the weak condition a.s. for ergodic scale-free random environments, establishing the corresponding a.s bounds.

ALT We give a framework for transporting vectors along Markov processes that may have jumps, without assuming a manifold or other specific geometric structure. We prove existence and uniqueness of the resulting transport. In doing so, we develop a theory of vector bundles defined quasi-everywhere, in which the vectors live, and an axiomatic framework for energy forms that determine the bundle and the transport.



















