arXiv subjects

Yuichi Yoshida

Publications and source records attributed to Yuichi Yoshida.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Cut Balance: Spectral Sparsification of the Nonlinear Directed Laplacian

Digraphs with constant cut balance admit nearly linear directed cut sparsifiers. This condition requires the total arc weights in the two directions of every cut to be within a constant factor of each other. We ask whether this condition also permits nearly linear spectral sparsification with respect to the energy of the nonlinear directed Laplacian. For a weighted digraph $G=(V,E,w)$, let \[ Q_G^+(x)=\sum_{(u,v)\in E}w_{uv}(x_u-x_v)_+^2, \qquad (t)_+:=\max\{t,0\}. \] This energy agrees with the outgoing-cut function on binary vectors. A spectral sparsifier is a nonnegatively reweighted subgraph that preserves $Q_G^+(x)$ within a factor of $1\pm\varepsilon$ simultaneously for all $x\in\mathbb R^V$. We show that cut balance alone does not yield nearly linear spectral sparsifiers: for constant error, the worst-case support size for simple unweighted Eulerian digraphs is $\widetilde\Theta(n^{3/2})$, although Eulerian digraphs are perfectly cut-balanced and admit nearly linear directed cut sparsifiers. In contrast, we prove that every $n$-vertex tournament has a spectral sparsifier with $\widetilde O(n/\varepsilon^3)$ arcs, without any assumption on its cut balance. This includes the transitive tournament, whose cut balance is unbounded. Thus perfect balance does not guarantee nearly linear spectral sparsification, while unbounded imbalance does not preclude it. Finally, we use convex duality to show that preserving $Q_G^+$ also preserves, for every feasible demand vector, the optimum quadratic cost of a nonnegative flow. Hence the guarantee contains information beyond directed cut values.

cs.DS↗

arXiv2026

A quantitative container characterization of one-sided testability

We give a quantitative combinatorial characterization of size-oblivious one-sided testability in the dense graph model, resolving a question of Alon, Fischer, Newman, and Shapira. For hereditary graph properties, we prove that one-sided testability is quantitatively equivalent to the existence of suitable hypergraph containers, a central and widely used tool in modern combinatorics. Combining this equivalence with the Alon-Shapira notion of semi-hereditariness yields a quantitative characterization of arbitrary graph properties. The correspondence is effective in both directions and provides explicit translations between tester complexity and container parameters. Our proof is regularity-free and extends uniformly to every fixed finite relational signature of bounded arity, including digraphs, coloured graphs, and hypergraphs. As applications, we obtain quantitative closure results for partition properties and testers for properties defined by the existence of a linearly large induced substructure.

math.CO↗

arXiv2026

Nonlinear Laplacians Improve Signed-Directed Graph Learning

While signed-directed graphs have been studied using linear Laplacians in the design of graph neural networks, relatively little research has focused on developing non-linear Laplacian operators for such networks. We introduce a non-linear Laplacian operator specific to signed and directed networks (NLSD). This non-linear operator extends the concepts of the signed Laplacian for signed graphs and the Laplacian for directed graphs. The NLSD calculates node-specific potentials based on features More precisely, if the potential discrepancy is not aligned with the edge direction, we ignore it (and vice versa) leveraging message-passing techniques only across edges where potential discrepancies align with the edge's direction. Utilizing this novel operator, we propose an efficient spectral GNN framework (NLSD-GNN). We conducted comprehensive evaluations focusing on node classification and link prediction, examining scenarios involving signed, directional, or both types of information. Our findings reveal that this spectral GNN framework not only integrates signed and directional data effectively but also achieves superior performance across diverse datasets.

cs.LG↗

arXiv2026

Sensitivity and Differential Privacy in Metric Voting with Distortion below Three

Voting rules aggregate individual preferences into collective decisions, but the rankings they receive contain only ordinal information. The metric distortion framework studies ordinal voting rules in settings where voters and candidates are embedded in an unknown metric space. Deterministic rules have optimal worst-case distortion $3$, while recent randomized rules break the $3$ barrier. We study whether such improvements can coexist with low worst-case sensitivity with respect to the Wasserstein distance of lotteries under one-voter deletion and approximate differential privacy under one-voter replacement. On the sensitivity side, we give a randomized rule with distortion at most $3-\varepsilon$ for an absolute constant $\varepsilon>0$ and, for $m$ candidates and $n$ voters, a worst-case sensitivity bound of $O((\log m+1)/n)$. On the privacy side, for every $\delta\in(0,1)$ and all $n$ above an absolute constant, we construct a variant rule whose mechanism releasing a single sampled winner has distortion at most $3-\varepsilon$ and is $(O((\log m+\log(1/\delta)+1)/n),\delta)$-differentially private. Both constructions use the same family of Gibbs distributions over constant-size candidate lists, with only the temperature parameter differing between the sensitivity and differential-privacy guarantees. Our analysis builds on the biased-metric viewpoint behind the recent improvement over the $3$ barrier and proves a stability property for the biased-metric ratio.

cs.GT↗

arXiv2026

Approximate Colorwise Tensorization of Entropy and Optimal Mixing of the Wang-Swendsen-Koteck\'y Dynamics

We study the mixing time of Wang-Swendsen-Koteck\'{y} (WSK) dynamics for uniformly sampling proper $q$-colorings. The WSK dynamics is widely used in statistical physics for sampling from the antiferromagnetic Potts model and can be considered a global counterpart of the flip dynamics, which currently yields the state-of-the-art bounds for sampling colorings in general graphs (Carlson and Vigoda, SODA 2025). However, despite its importance, the tools for analyzing such dynamics remain limited. We develop new tools that enable us to analyze the mixing time of the WSK dynamics through the lens of relative entropy contraction. We introduce new criteria for multi-spin distributions: approximate colorwise tensorization of entropy (ACTE) and approximate colorwise subadditivity of entropy (ACSE). These criteria provide a colorwise counterpart to standard vertex-wise entropy factorization principles, and expose a form of color symmetry beyond coordinate-wise analyses. We also develop new inductive approaches for establishing such criteria on specific types of graphs, which can be viewed as local-to-global arguments for proving high-dimensional functional inequalities in a graph-theoretic sense. As concrete applications, we establish an optimal $O_q(\log n)$ mixing time for the WSK dynamics on chordal and outerplanar graphs, down to the optimal number of colors. Because trees and line graphs of trees are chordal, the result covers both vertex and edge colorings of trees. Our results work in a regime that bypasses the irreducibility threshold for Glauber dynamics while also improving the best known mixing time bounds (Carlson, Chen, Feng and Vigoda, SODA 2025).

cs.DS↗

arXiv2026

Sensitivity Lower Bounds via Locally Testable Codes

Sensitivity quantifies how far an algorithm's output can move in Hamming distance when a single input element is perturbed. We present a general scheme turning any locally testable code (LTC) into a sensitivity lower bound for the CSP encoded by the code. Instantiating it with the $c^3$-LTC yields a constant $\varepsilon > 0$ for which every $(1-\varepsilon)$-approximation algorithm for satisfiable Max E3LIN2 has sensitivity $\Omega(n)$, strengthening the previous $\Omega(n^\delta)$ lower bound known only for general instances. Standard reductions give an $n^{1-O(\varepsilon)}$ lower bound for $n^{-\varepsilon}$-approximation algorithms for maximum clique, and an $\Omega(k)$ bound for $(1-\varepsilon)$-approximation algorithms for maximum $k$-coverage, among others. These lower bounds match trivial upper bounds and imply that even slightly stable algorithms cannot achieve these approximations. A second instantiation, using a simple repetition code, shows that any $(1-\varepsilon)$-approximation algorithm for Max Cut on bipartite graphs has sensitivity $\Omega(1/\varepsilon)$ as long as $\varepsilon = O(1/\sqrt{n})$, extending the prior result for exact algorithms (the regime $\varepsilon < 1/n$). Thus even on bipartite graphs, where a perfect cut always exists, near-optimal solutions cannot be maintained stably. Our sensitivity lower bounds have two applications. First, they yield averaged sensitivity lower bounds, implying that any nearly optimal randomized algorithm for Max E3SAT has linearly many output bits that, after fixing the random seed, are Boolean functions with large influence. Second, via the sensitivity-to-locality connection, they imply locality lower bounds in the non-signaling model, which generalizes $\mathsf{LOCAL}$ and quantum-$\mathsf{LOCAL}$.

cs.DS↗

arXiv2026

Tolerant Testing for Unique Games

We give tolerant testers with sublinear query complexity in the adjacency-list model for Unique Games. Prior tolerant testers required structural assumptions such as expansion or clusterability. For Unique Games, the tester distinguishes instances whose optimum fraction of violated constraints is at most $\varepsilon$ from those whose optimum is at least $\rho$, for $0<\varepsilon<\rho<1$, assuming $\varepsilon\log n\lesssim\rho^4$. On instances with $n$ vertices and $m$ constraints, it uses $\widetilde O(\sqrt m\,\rho^{-13/2}+n\rho^{-2}/\sqrt m)$ queries. We also give a specialized tester for bipartiteness, the $Q=2$ transposition case of Unique Games. Exploiting its signed structure, the tester achieves substantially better tolerance and query-complexity guarantees than the generic Unique Games tester. Writing $\lambda=\rho/(1+\log(1/\rho))$, the bipartiteness tester distinguishes graphs that can be made bipartite by deleting at most an $\varepsilon$ fraction of edges from graphs in which every bipartition has at least a $\rho$ fraction of edges with both endpoints on the same side, assuming $\varepsilon\log n\lesssim\lambda^2$, using $\widetilde O(\sqrt m/\lambda^2+n/(\sqrt m\,\lambda))$ queries.

cs.DS↗

arXiv2026

Solving Hypergraph Laplacian Systems in Almost-Linear Time

For a connected weighted hypergraph, we give a randomized almost-linear-time solver for the Poisson problem for the cut-based hypergraph Laplacian in the natural input size $P=\sum_{e\in E}|e|$, the sum of hyperedge sizes. For every fixed constant $C>0$, our randomized algorithm runs in $P^{1+o(1)}$ time and, with high probability over its internal randomness, returns a primal point and a dual certificate, with additive optimality gap at most $\exp(-\log^C P)$. A key step is to rewrite the Fenchel dual as a convex-flow problem on an auxiliary $O(P)$-arc graph, yielding a near-optimal dual flow. The main difficulty is primal recovery, because this flow does not by itself determine a primal potential. Our main new ingredient is a recovery theorem showing that, for primal recovery, the detailed routing of the dual flow inside each hyperedge gadget can be discarded: one nonnegative scalar per hyperedge is enough. After the necessary finite-precision rounding, these scalars define a linear-cost min-cost-flow instance on the auxiliary graph, and solving it exactly recovers a primal potential. Finally, a ground-vertex reduction from regularized objectives to the Poisson solver gives randomized almost-linear-time resolvent/proximal primitives for the same cut-based hypergraph Laplacian.

cs.DS↗

arXiv2026

Lower Bounds for Testing Directed Acyclicity in the Unidirectional Bounded-Degree Model

We study property testing of directed acyclicity in the unidirectional bounded-degree oracle model, where a query to a vertex reveals its outgoing neighbors. We prove that there exist absolute constants $d_0\in\mathbb{N}$ and $\varepsilon>0$ such that for every constant $d\ge d_0$, any one-sided $\varepsilon$-tester for acyclicity on $n$-vertex digraphs of maximum outdegree at most $d$ requires $\widetilde{\Omega}(n^{2/3})$ queries. This improves the previous $\widetilde{\Omega}(n^{5/9})$ lower bound for one-sided testing of acyclicity in the same model. We also prove that, under the same degree assumption, any two-sided $\varepsilon$-tester requires $\Omega(\sqrt n)$ queries, improving the previous $\Omega(n^{1/3})$ lower bound. We further prove an $\Omega(n)$ lower bound for tolerant testing for some absolute constant outdegree bound $d$ by reduction from bounded-degree $3$-colorability.

cs.DS↗

arXiv2026

Non-Signaling Locality Lower Bounds for Dominating Set

Minimum dominating set is a basic local covering problem and a core task in distributed computing. Despite extensive study, in the classic LOCAL model there exist significant gaps between known algorithms and lower bounds. Chang and Li prove an $\Omega(\log n)$-locality lower bound for a constant factor approximation, while Kuhn--Moscibroda--Wattenhofer gave an algorithm beating this bound beyond $\log \Delta$-approximation, along with a weaker lower bound for this degree-dependent setting scaling roughly with $\min\{\log \Delta/\log\log \Delta,\sqrt{\log n/\log\log n}\}$. Unfortunately, this latter bound is weak for small $\Delta$, and never recovers the Chang--Li bound, leaving central questions: does $O(\log \Delta)$-approximation require $\Omega(\log n)$ locality, and do such bounds extend beyond LOCAL? In this work, we take a major step toward answering these questions in the non-signaling model, which strictly subsumes the LOCAL, quantum-LOCAL, and bounded-dependence settings. We prove every $O(\log\Delta)$-approximate non-signaling distribution for dominating set requires locality $\Omega(\log n/(\log\Delta \cdot \mathrm{poly}\log\log\Delta))$. Further, we show for some $\beta \in (0,1)$, every $O(\log^\beta \Delta)$-approximate non-signaling distribution requires locality $\Omega(\log n/\log\Delta)$, which combined with the KMW bound yields a degree-independent $\Omega(\sqrt{\log n/\log\log n})$ quantum-LOCAL lower bound for $O(\log^\beta\Delta)$-approximation algorithms. The proof is based on two new low-soundness sensitivity lower bounds for label cover, one via Impagliazzo--Kabanets--Wigderson-style parallel repetition with degree reduction and one from a sensitivity-preserving reworking of the Dinur--Harsha framework, together with the reductions from label cover to set cover to dominating set and the sensitivity-to-locality transfer theorem of Fleming and Yoshida.

cs.DS↗

arXiv2026

Testing Monotonicity of Real-Valued Functions on DAGs

We study monotonicity testing of real-valued functions on directed acyclic graphs (DAGs) with $n$ vertices. Let $m$ and $\ell$ be the numbers of edges in the transitive reduction and the transitive closure, respectively. For $1\le c\le d\le2$, define $u(c,d):=\min\left\{\frac12,\frac c3,\frac{c+d}{2}-1\right\}$. We show that every family of DAGs with $m=n^{c+o(1)}$ and $\ell=n^{d+o(1)}$ admits, for every fixed $\varepsilon\in(0,1)$, a non-adaptive tester with one-sided error that uses $O_\varepsilon(n^{u(c,d)+o(1)})$ queries. Conversely, we show that for every sufficiently small fixed $\varepsilon>0$ and every fixed $(c,d)$, there are families of DAGs satisfying $m=n^{c+o(1)}$ and $\ell=n^{d+o(1)}$ on which every randomized non-adaptive tester, even with two-sided error, requires $n^{u(c,d)-o(1)}$ queries, making the upper bound tight up to a factor $n^{o(1)}$. Our main technical contribution is a lower-bound technique based on Ruzsa--Szemer\'edi families of positive matchings.

cs.DS↗

arXiv2026

From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model

We study online learning in the random-order model, where the multiset of loss functions is chosen adversarially but revealed in a uniformly random order. By extending the batch-to-online transformation of Dong and Yoshida (2023), we show that if an offline algorithm enjoys a $(1+\varepsilon)$-approximation guarantee, an average sensitivity bound controlled by a function $\varphi(\varepsilon)$, and stability with respect to $\varepsilon$, then we can obtain a small-loss regret bound typically of order $\tilde O(\varphi^{\star}(\mathrm{OPT}_T))$, where $\varphi^{\star}$ is the concave conjugate of $\varphi$, $\mathrm{OPT}_T$ is the offline optimum over $T$ rounds, and $\tilde O$ hides polylogarithmic factors in $T$. Our result refines their original $(1+\varepsilon)$-approximate regret guarantee and applies to a broad class of problems, including online $k$-means clustering and online low-rank approximation. We further apply our approach to online submodular function minimization using $(1\pm\varepsilon)$-cut sparsifiers of submodular hypergraphs, obtaining a small-loss regret bound of $\tilde O(n^3 + n^{3/4}\mathrm{OPT}_T^{3/4})$, where $n$ is the ground-set size; we also demonstrate its applicability to online $\ell_1$ regression. Our work sheds light on the power of sparsification and related algorithmic techniques in achieving small-loss regret bounds in the random-order model, without requiring structural assumptions on loss functions, such as linearity or smoothness.

stat.ML↗

arXiv2026

Noise Stability of Transformer Models

Understanding simplicity biases in deep learning offers a promising path toward developing reliable AI. A common metric for this, inspired by Boolean function analysis, is average sensitivity, which captures a model's robustness to single-token perturbations. We argue that average sensitivity has two key limitations: it lacks a natural generalization to real-valued domains and fails to explain the "junta-like" input dependence we empirically observe in modern LLMs. To address these limitations, we propose noise stability as a more comprehensive simplicity metric. Noise stability expresses a model's robustness to correlated noise applied to all input coordinates simultaneously. We provide a theoretical analysis of noise stability for single-layer attention and ReLU MLP layers and tackle the multi-layer propagation problem with a covariance interval propagation approach. Building on this theory, we develop a practical noise stability regularization method. Experiments on algorithmic and next-token-prediction tasks show that our regularizer consistently catalyzes grokking and accelerates training by approximately $35\%$ and $75\%$ respectively. Our results sculpt a new connection between signal propagation in neural networks and interpretability, with noise stability emerging as a powerful tool for understanding and improving modern Transformers.

cs.LG↗

arXiv2025

Low-Sensitivity Matching via Sampling from Gibbs Distributions

In this work, we study the maximum matching problem from the perspective of sensitivity. The sensitivity of an algorithm $A$ on a graph $G$ is defined as the maximum Wasserstein distance between the output distributions of $A$ on $G$ and on $G - e$, where $G - e$ is the graph obtained by deleting an edge $e$ from $G$. The maximum is taken over all edges $e$, and the underlying metric for the Wasserstein distance is the Hamming distance. We first show that for any $\varepsilon > 0$, there exists a polynomial-time $(1 - \varepsilon)$-approximation algorithm with sensitivity $\Delta^{O(1/\varepsilon)}$, where $\Delta$ is the maximum degree of the input graph. The algorithm is based on sampling from the Gibbs distribution over matchings and runs in time $O_{\varepsilon, \Delta}(m \log m)$, where $m$ is the number of edges in the graph. This result significantly improves the previously known sensitivity bounds. Next, we present significantly faster algorithms for planar and bipartite graphs as a function of $\varepsilon$ and $\Delta$, which run in time $\mathrm{poly}(n/\varepsilon)$. This improvement is achieved by designing a more efficient algorithm for sampling matchings from the Gibbs distribution in these graph classes, which improves upon the previous best in terms of running time. Finally, for general graphs with potentially unbounded maximum degree, we show that there exists a polynomial-time $(1 - \varepsilon)$-approximation algorithm with sensitivity $\sqrt{n} \cdot (\varepsilon^{-1} \log n)^{O(1/\varepsilon)}$, improving upon the previous best bound of $O(n^{1/(1+\varepsilon^2)})$.

cs.DS↗

arXiv2025

$O(\log n)$-Approximation Algorithms for Bipartiteness Ratio

We propose an $O(\log n)$-approximation algorithm for the bipartiteness ratio of undirected graphs introduced by Trevisan (SIAM Journal on Computing, vol. 41, no. 6, 2012), where $n$ is the number of vertices. Our approach extends the cut-matching game framework for sparsest cut to the bipartiteness ratio, and requires only $\mathop{\mathrm{polylog}} n$ many single-commodity undirected maximum flow computations. Therefore, with the current fastest undirected max-flow algorithms, it runs in almost linear time. Along the way, we introduce the concept of well-linkedness for skew-symmetric graphs and prove a novel characterization of bipartiteness ratio in terms of well-linkedness in an auxiliary skew-symmetric graph, which may be of independent interest. As an application, we devise an $\tilde{O}(mn)$-time algorithm for the minimum uncut problem: given a graph whose optimal cut leaves an $\eta$ fraction of edges uncut, we find a cut that leaves only an $O(\log n \log(1/\eta)) \cdot \eta$ fraction of edges uncut, where $m$ is the number of edges. Finally, we propose a directed analogue of the bipartiteness ratio, and we give a polynomial-time algorithm that achieves an $O(\log n)$ approximation for this measure via a directed Leighton--Rao-style embedding. We also propose an algorithm for the minimum directed uncut problem with a guarantee similar to that for the minimum uncut problem.

cs.DS↗

arXiv2025

From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning

The epidemic failure of replicability across empirical science and machine learning has recently motivated the formal study of replicable learning algorithms [Impagliazzo et al. (2022)]. In batch settings where data comes from a fixed i.i.d. source (e.g., hypothesis testing, supervised learning), the design of data-efficient replicable algorithms is now more or less understood. In contrast, there remain significant gaps in our knowledge for control settings like reinforcement learning where an agent must interact directly with a shifting environment. Karbasi et. al show that with access to a generative model of an environment with $S$ states and $A$ actions (the RL 'batch setting'), replicably learning a near-optimal policy costs only $\tilde{O}(S^2A^2)$ samples. On the other hand, the best upper bound without a generative model jumps to $\tilde{O}(S^7 A^7)$ [Eaton et al. (2024)] due to the substantial difficulty of environment exploration. This gap raises a key question in the broader theory of replicability: Is replicable exploration inherently more expensive than batch learning? Is sample-efficient replicable RL even possible? In this work, we (nearly) resolve this problem (for low-horizon tabular MDPs): exploration is not a significant barrier to replicable learning! Our main result is a replicable RL algorithm on $\tilde{O}(S^2A)$ samples, bridging the gap between the generative and episodic settings. We complement this with a matching $\tilde{\Omega}(S^2A)$ lower bound in the generative setting (under the common parallel sampling assumption) and an unconditional lower bound in the episodic setting of $\tilde{\Omega}(S^2)$ showcasing the near-optimality of our algorithm with respect to the state space $S$.

cs.LG↗

arXiv2025

Courcelle's Theorem for Lipschitz Continuity

Lipschitz continuity of algorithms, introduced by Kumabe and Yoshida (FOCS'23), measures the stability of an algorithm against small input perturbations. Algorithms with small Lipschitz continuity are desirable, as they ensure reliable decision-making and reproducible scientific research. Several studies have proposed Lipschitz continuous algorithms for various combinatorial optimization problems, but these algorithms are problem-specific, requiring a separate design for each problem. To address this issue, we provide the first algorithmic meta-theorem in the field of Lipschitz continuous algorithms. Our result can be seen as a Lipschitz continuous analogue of Courcelle's theorem, which offers Lipschitz continuous algorithms for problems on bounded-treewidth graphs. Specifically, we consider the problem of finding a vertex set in a graph that maximizes or minimizes the total weight, subject to constraints expressed in monadic second-order logic (MSO_2). We show that for any $\varepsilon>0$, there exists a $(1\pm \varepsilon)$-approximation algorithm for the problem with a polylogarithmic Lipschitz constant on bounded treewidth graphs. On such graphs, our result outperforms most existing Lipschitz continuous algorithms in terms of approximability and/or Lipschitz continuity. Further, we provide similar results for problems on bounded-clique-width graphs subject to constraints expressed in MSO_1. Additionally, we construct a Lipschitz continuous version of Baker's decomposition using our meta-theorem as a subroutine.

cs.DS↗

arXiv2025

The minimum number of vertices and edges of connected graphs with ind-match$(G) = p$, min-match$(G) = q$ and match$(G) = r$

Let ind-match$(G)$, min-match$(G)$ and match$(G)$ denote the induced matching number, minimum matching number and matching number of a graph $G$, respectively. It is known that ind-match$(G) \leq $ min-match$(G) \leq {\rm match}(G) \leq$ 2min-match$(G)$ holds. In the present paper, we investigate the minimum number of vertices and edges of connencted simple graphs $G$ with ind-match$(G) = p$, min-match$(G) = q$ and ${\rm match}(G) = r$ for pair of integers $p, q, r$ such that $1 \leq p \leq q \leq r \leq 2q$.

math.CO↗