An official website of the United States government
Abstract The 4 N {4N} -carpets are a class of infinitely ramified self-similar fractals with a large group of symmetries. For a 4 N {4N} -carpet F , let { F n } n ≥ 0 {\{F_{n}\}_{n\geq 0}} be the natural decreasing sequence of compact pre-fractal approximations with ⋂ n F n = F {\bigcap_{n}F_{n}=F} . On each F n {F_{n}} , let ℰ ( u , v ) = ∫ F N ∇ u ⋅ ∇ v d x {\mathcal{E}(u,v)=\int_{F_{N}}\nabla u\cdot\nabla v\,dx} be the classical Dirichlet form and u n {u_{n}} be the unique harmonic function on F n {F_{n}} satisfying a mixed boundary value problem corresponding to assigning a constant potential between two specific subsets of the boundary. Using a method introduced by [M. T. Barlow and R. F. Bass,On the resistance of the Sierpiński carpet, Proc. Roy. Soc. Lond. Ser. A 431 (1990), no. 1882, 345–360], we prove a resistance estimate of the following form: there is ρ = ρ ( N ) > 1 {\rho=\rho(N)>1} such that ℰ ( u n , u n ) ρ n {\mathcal{E}(u_{n},u_{n})\rho^{n}} is bounded above and below by constants independent of n . Such estimates have implications for the existence and scaling properties of Brownian motion on F .
more »
« less
Condition-number-independent Convergence Rate of Riemannian Hamiltonian Monte Carlo with Numerical Integrators
We study the convergence rate of discretized Riemannian Hamiltonian Monte Carlo on sampling from distributions in the form of e^{−f(x)} on a convex body M ⊂ R^n. We show that for distributions in the form of e−^{a x} on a polytope with m constraints, the convergence rate of a family of commonly-used integrators is independent of ∥a∥_2 and the geometry of the polytope. In particular, the implicit midpoint method (IMM) and the generalized Leapfrog method (LM) have a mixing time of mn^3 to achieve ϵ total variation distance to the target distribution. These guarantees are based on a general bound on the convergence rate for densities of the form e^{−f(x)} in terms of parameters of the manifold and the integrator. Our theoretical guarantee complements the empirical results of our old result, which shows that RHMC with IMM can sample ill-conditioned, non-smooth and constrained distributions in very high dimension efficiently in practice.
more »
« less
- Award ID(s):
- 1839116
- PAR ID:
- 10482062
- Publisher / Repository:
- COLT 2013
- Date Published:
- Journal Name:
- COLT 2013
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present a new algorithm for learning unknown gov- erning equations from trajectory data, using a family of neural net- works. Given samples of solutions x(t) to an unknown dynamical system x ̇ (t) = f (t, x(t)), we approximate the function f using a family of neural networks. We express the equation in integral form and use Euler method to predict the solution at every successive time step using at each iter- ation a different neural network as a prior for f. This procedure yields M-1 time-independent networks, where M is the number of time steps at which x(t) is observed. Finally, we obtain a single function f(t,x(t)) by neural network interpolation. Unlike our earlier work, where we numer- ically computed the derivatives of data, and used them as target in a Lipschitz regularized neural network to approximate f, our new method avoids numerical differentiations, which are unstable in presence of noise. We test the new algorithm on multiple examples in a high-noise setting. We empirically show that generalization and recovery of the governing equation improve by adding a Lipschitz regularization term in our loss function and that this method improves our previous one especially in the high-noise regime, when numerical differentiation provides low qual- ity target data. Finally, we compare our results with other state of the art methods for system identification.more » « less
-
We obtain partial improvement toward the pointwise convergence problem of Schrödinger solutions, in the general setting of fractal measure. In particular, we show that, for $$n\geqslant 3$$ , $$\lim _{t\rightarrow 0}e^{it\unicode[STIX]{x1D6E5}}f(x)$$ $=f(x)$ almost everywhere with respect to Lebesgue measure for all $$f\in H^{s}(\mathbb{R}^{n})$$ provided that $s>(n+1)/2(n+2)$ . The proof uses linear refined Strichartz estimates. We also prove a multilinear refined Strichartz using decoupling and multilinear Kakeya.more » « less
-
null (Ed.)We study the application of iterative first-order methods to the problem of computing equilibria of large-scale two-player extensive-form games. First-order methods must typically be instantiated with a regularizer that serves as a distance-generating function for the decision sets of the players. For the case of two-player zero-sum games, the state-of-the-art theoretical convergence rate for Nash equilibrium is achieved by using the dilated entropy function. In this paper, we introduce a new entropy-based distance-generating function for two-player zero-sum games, and show that this function achieves significantly better strong convexity properties than the dilated entropy, while maintaining the same easily-implemented closed-form proximal mapping. Extensive numerical simulations show that these superior theoretical properties translate into better numerical performance as well. We then generalize our new entropy distance function, as well as general dilated distance functions, to the scaled extension operator. The scaled extension operator is a way to recursively construct convex sets, which generalizes the decision polytope of extensive-form games, as well as the convex polytopes corresponding to correlated and team equilibria. By instantiating first-order methods with our regularizers, we develop the first accelerated first-order methods for computing correlated equilibra and ex-ante coordinated team equilibria. Our methods have a guaranteed 1/T rate of convergence, along with linear-time proximal updates.more » « less
-
Lawson, Tracy (Ed.)Abstract Shifts in stomatal trait distributions across contrasting environments and their linkage with ecosystem productivity at large spatial scales have been unclear. Here, we measured the maximum stomatal conductance (g), stomatal area fraction (f), and stomatal space-use efficiency (e, the ratio of g to f) of 800 plant species ranging from tropical to cold-temperate forests, and determined their values for community-weighted mean, variance, skewness, and kurtosis. We found that the community-weighted means of g and f were higher in drier sites, and thus, that drought ‘avoidance’ by water availability-driven growth pulses was the dominant mode of adaptation for communities at sites with low water availability. Additionally, the variance of g and f was also higher at arid sites, indicating greater functional niche differentiation, whereas that for e was lower, indicating the convergence in efficiency. When all other stomatal trait distributions were held constant, increasing kurtosis or decreasing skewness of g would improve ecosystem productivity, whereas f showed the opposite patterns, suggesting that the distributions of inter-related traits can play contrasting roles in regulating ecosystem productivity. These findings demonstrate the climatic trends of stomatal trait distributions and their significance in the prediction of ecosystem productivity.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
