More Like this

1. Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth

   https://doi.org/10.1162/neco_a_01364  

   Shen, Zuowei; Yang, Haizhao; Zhang, Shijun (January 2021, Neural Computation)

   null (Ed.)

   A new network with super-approximation power is introduced. This network is built with Floor (⌊x⌋) or ReLU (max{0,x}) activation function in each neuron; hence, we call such networks Floor-ReLU networks. For any hyperparameters N∈N+ and L∈N+, we show that Floor-ReLU networks with width max{d,5N+13} and depth 64dL+3 can uniformly approximate a Hölder function f on [0,1]d with an approximation error 3λdα/2N-αL, where α∈(0,1] and λ are the Hölder order and constant, respectively. More generally for an arbitrary continuous function f on [0,1]d with a modulus of continuity ωf(·), the constructive approximation rate is ωf(dN-L)+2ωf(d)N-L. As a consequence, this new class of networks overcomes the curse of dimensionality in approximation power when the variation of ωf(r) as r→0 is moderate (e.g., ωf(r)≲rα for Hölder continuous functions), since the major term to be considered in our approximation rate is essentially d times a function of N and L independent of d within the modulus of continuity. 

   more » « less
2. On finite energy monopoles on $$C x \Sigma$$.

   Wang, Donghao (July 2019, ArXiv.org)

   Let $$X=\mathbb{C}\times\Sigma$$ be the product of the complex plane and a compact Riemann surface. We establish a classification theorem of solutions to the Seiberg-Witten equation on $$X$$ with finite analytic energy. The spin bundle $$S^+\to X$$ splits as $$L^+\oplus L^-$$. When $$2-2g\leq c_1(S^+)[\Sigma]<0$$, the moduli space is in bijection with the moduli space of pairs $$((L^+,\bar{\partial}), f)$$ where $$(L^+,\bar{\partial})$$ is a holomorphic structure on $L^+$ and $$f: \mathbb{C}\to H^0(\Sigma, L^+,\bar{\partial})$$ is a polynomial map. Moreover, the solution has analytic energy $$-4\pi^2d\cdot c_1(S^+)[\Sigma]$$ if $$f$$ has degree $$d$$. When $$c_1(S^+)=0$$, all solutions are reducible and the moduli space is the space of flat connections on $$\bigwedge^2 S^+$$. We also estimate the decay rate at infinity for these solutions. 

   more » « less
3. On the Strict Majorant Property in Arbitrary Dimensions

   https://doi.org/10.1093/qmath/haac021  

   Gressman, P T; Guo, S; Pierce, L B; Roos, J; Yung, P -L (July 2022, The Quarterly Journal of Mathematics)

   Abstract In this work we study d-dimensional majorant properties. We prove that a set of frequencies in $$\mathbb{Z}^d$$ satisfies the strict majorant property on $L^p([0,1]^d)$ for all p > 0 if and only if the set is affinely independent. We further construct three types of violations of the strict majorant property. Any set of at least d + 2 frequencies in $$\mathbb{Z}^d$$ violates the strict majorant property on $L^p([0,1]^d)$ for an open interval of $$p \not\in 2\mathbb{N}$$ of length 2. Any infinite set of frequencies in $$\mathbb{Z}^d$$ violates the strict majorant property on $L^p([0,1]^d)$ for an infinite sequence of open intervals of $$p \not\in 2\mathbb{N}$$ of length 2. Finally, given any p > 0 with $$p \not\in 2\mathbb{N}$$, we exhibit a set of d + 2 frequencies on the moment curve in $$\mathbb{R}^d$$ that violate the strict majorant property on $L^p([0,1]^d).$ 

   more » « less
4. AND testing and robust judgement aggregation

   https://doi.org/10.1145/3357713.3384254  

   Filmus, Y; Lifshitz, N; Minzer, D; Mossel, E. (June 2020, STOC 2020: Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing)

   A function f∶{0,1}n→ {0,1} is called an approximate AND-homomorphism if choosing x,y∈n uniformly at random, we have that f(x∧ y) = f(x)∧ f(y) with probability at least 1−ε, where x∧ y = (x1∧ y1,…,xn∧ yn). We prove that if f∶ {0,1}n → {0,1} is an approximate AND-homomorphism, then f is δ-close to either a constant function or an AND function, where δ(ε) → 0 as ε→ 0. This improves on a result of Nehama, who proved a similar statement in which δ depends on n. Our theorem implies a strong result on judgement aggregation in computational social choice. In the language of social choice, our result shows that if f is ε-close to satisfying judgement aggregation, then it is δ(ε)-close to an oligarchy (the name for the AND function in social choice theory). This improves on Nehama’s result, in which δ decays polynomially with n. Our result follows from a more general one, in which we characterize approximate solutions to the eigenvalue equation f = λ g, where is the downwards noise operator f(x) = y[f(x ∧ y)], f is [0,1]-valued, and g is {0,1}-valued. We identify all exact solutions to this equation, and show that any approximate solution in which f and λ g are close is close to an exact solution. 

   more » « less
5. Realizing trees of configurations in thin sets

   https://doi.org/10.2140/pjm.2025.335.355  

   Greenleaf, Allan; Iosevich, Alex; Taylor, Krystal (January 2025, Pacific Journal of Mathematics)

   Let $$\phi(x,y)$$ be a continuous function, smooth away from the diagonal, such that, for some $$\alpha>0$$, the associated generalized Radon transforms \begin{equation} \label{Radon} R_t^{\phi}f(x)=\int_{\phi(x,y)=t} f(y) \psi(y) d\sigma_{x,t}(y) \end{equation} map $$L^2({\mathbb R}^d) \to H^{\alpha}({\mathbb R}^d)$$ for all $t>0$. Let $$E$$ be a compact subset of $${\mathbb R}^d$$ for some $$d \ge 2$$, and suppose that the Hausdorff dimension of $$E$$ is $$>d-\alpha$$. We show that any tree graph $$T$$ on $k+1$ ($$k \ge 1$$) vertices is realizable in $$E$$, in the sense that there exist distinct $$x^1, x^2, \dots, x^{k+1} \in E$$ and $t>0$ such that the $$\phi$$-distance $$\phi(x^i, x^j)$$ is equal to $$t$$ for all pairs $(i,j)$ corresponding to the edges of the graph $$T$$. 

   more » « less