arXiv subjects

Yujia Jin

Publications and source records attributed to Yujia Jin.

At least 19 recordsLinked to original sources

arXiv2025

Reusing Samples in Variance Reduction

We provide a general framework to improve trade-offs between the number of full batch and sample queries used to solve structured optimization problems. Our results apply to a broad class of randomized optimization algorithms that iteratively solve sub-problems to high accuracy. We show that such algorithms can be modified to reuse the randomness used to query the input across sub-problems. Consequently, we improve the trade-off between the number of gradient (full batch) and individual function (sample) queries for finite sum minimization, the number of matrix-vector multiplies (full batch) and random row (sample) queries for top-eigenvector computation, and the number of matrix-vector multiplies with the transition matrix (full batch) and generative model (sample) queries for optimizing Markov Decision Processes. To facilitate our analysis we introduce the notion of pseudo-independent algorithms, a generalization of pseudo-deterministic algorithms [Gat and Goldwasser 2011], that quantifies how independent the output of a randomized algorithm is from a randomness source.

cs.DS↗

arXiv2025

Catoni Contextual Bandits are Robust to Heavy-tailed Rewards

Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed rewards or rewards where the worst-case range can be substantially larger than the variance. In this paper, we develop an algorithmic approach building on Catoni's estimator from robust statistics, and apply it to contextual bandits with general function approximation. When the variance of the reward at each round is known, we use a variance-weighted regression approach and establish a regret bound that depends only on the cumulative reward variance and logarithmically on the reward range $R$ as well as the number of rounds $T$. For the unknown-variance case, we further propose a careful peeling-based algorithm and remove the need for cumbersome variance estimation. With additional dependence on the fourth moment, our algorithm also enjoys a variance-based bound with logarithmic reward-range dependence. Moreover, we demonstrate the optimality of the leading-order term in our regret bound through a matching lower bound.

stat.ML↗

arXiv2024

Faster Spectral Density Estimation and Sparsification in the Nuclear Norm

We consider the problem of estimating the spectral density of the normalized adjacency matrix of an $n$-node undirected graph. We provide a randomized algorithm that, with $O(nε^{-2})$ queries to a degree and neighbor oracle and in $O(nε^{-3})$ time, estimates the spectrum up to $ε$ accuracy in the Wasserstein-1 metric. This improves on previous state-of-the-art methods, including an $O(nε^{-7})$ time algorithm from [Braverman et al., STOC 2022] and, for sufficiently small $ε$, a $2^{O(ε^{-1})}$ time method from [Cohen-Steiner et al., KDD 2018]. To achieve this result, we introduce a new notion of graph sparsification, which we call nuclear sparsification. We provide an $O(nε^{-2})$-query and $O(nε^{-2})$-time algorithm for computing $O(nε^{-2})$-sparse nuclear sparsifiers. We show that this bound is optimal in both its sparsity and query complexity, and we separate our results from the related notion of additive spectral sparsification. Of independent interest, we show that our sparsification method also yields the first deterministic algorithm for spectral density estimation that scales linearly with $n$ (sublinear in the representation size of the graph).

cs.DS↗

arXiv2024

Truncated Variance Reduced Value Iteration

We provide faster randomized algorithms for computing an $ε$-optimal policy in a discounted Markov decision process with $A_{\text{tot}}$-state-action pairs, bounded rewards, and discount factor $γ$. We provide an $\tilde{O}(A_{\text{tot}}[(1 - γ)^{-3}ε^{-2} + (1 - γ)^{-2}])$-time algorithm in the sampling setting, where the probability transition matrix is unknown but accessible through a generative model which can be queried in $\tilde{O}(1)$-time, and an $\tilde{O}(s + (1-γ)^{-2})$-time algorithm in the offline setting where the probability transition matrix is known and $s$-sparse. These results improve upon the prior state-of-the-art which either ran in $\tilde{O}(A_{\text{tot}}[(1 - γ)^{-3}ε^{-2} + (1 - γ)^{-3}])$ time [Sidford, Wang, Wu, Ye 2018] in the sampling setting, $\tilde{O}(s + A_{\text{tot}} (1-γ)^{-3})$ time [Sidford, Wang, Wu, Yang, Ye 2018] in the offline setting, or time at least quadratic in the number of states using interior point methods for linear programming. We achieve our results by building upon prior stochastic variance-reduced value iteration methods [Sidford, Wang, Wu, Yang, Ye 2018]. We provide a variant that carefully truncates the progress of its iterates to improve the variance of new variance-reduced sampling procedures that we introduce to implement the steps. Our method is essentially model-free and can be implemented in $\tilde{O}(A_{\text{tot}})$-space when given generative model access. Consequently, our results take a step in closing the sample-complexity gap between model-free and model-based methods.

cs.LG↗

arXiv2023

A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions

We design algorithms for minimizing $\max_{i\in[n]} f_i(x)$ over a $d$-dimensional Euclidean or simplex domain. When each $f_i$ is $1$-Lipschitz and $1$-smooth, our method computes an $ε$-approximate solution using $\widetilde{O}(n ε^{-1/3} + ε^{-2})$ gradient and function evaluations, and $\widetilde{O}(n ε^{-4/3})$ additional runtime. For large $n$, our evaluation complexity is optimal up to polylogarithmic factors. In the special case where each $f_i$ is linear -- which corresponds to finding a near-optimal primal strategy in a matrix game -- our method finds an $ε$-approximate solution in runtime $\widetilde{O}(n (d/ε)^{2/3} + nd + dε^{-2})$. For $n>d$ and $ε=1/\sqrt{n}$ this improves over all existing first-order methods. When additionally $d = ω(n^{8/11})$ our runtime also improves over all known interior point methods. Our algorithm combines three novel primitives: (1) A dynamic data structure which enables efficient stochastic gradient estimation in small $\ell_2$ or $\ell_1$ balls. (2) A mirror descent algorithm tailored to our data structure implementing an oracle which minimizes the objective over these balls. (3) A simple ball oracle acceleration framework suitable for non-Euclidean geometry.

cs.DS↗

arXiv2023

ReSQueing Parallel and Private Stochastic Convex Optimization

We introduce a new tool for stochastic convex optimization (SCO): a Reweighted Stochastic Query (ReSQue) estimator for the gradient of a function convolved with a (Gaussian) probability density. Combining ReSQue with recent advances in ball oracle acceleration [CJJJLST20, ACJJS21], we develop algorithms achieving state-of-the-art complexities for SCO in parallel and private settings. For a SCO objective constrained to the unit ball in $\mathbb{R}^d$, we obtain the following results (up to polylogarithmic factors). We give a parallel algorithm obtaining optimization error $ε_{\text{opt}}$ with $d^{1/3}ε_{\text{opt}}^{-2/3}$ gradient oracle query depth and $d^{1/3}ε_{\text{opt}}^{-2/3} + ε_{\text{opt}}^{-2}$ gradient queries in total, assuming access to a bounded-variance stochastic gradient estimator. For $ε_{\text{opt}} \in [d^{-1}, d^{-1/4}]$, our algorithm matches the state-of-the-art oracle depth of [BJLLS19] while maintaining the optimal total work of stochastic gradient descent. Given $n$ samples of Lipschitz loss functions, prior works [BFTT19, BFGT20, AFKT21, KLL21] established that if $n \gtrsim d ε_{\text{dp}}^{-2}$, $(ε_{\text{dp}}, δ)$-differential privacy is attained at no asymptotic cost to the SCO utility. However, these prior works all required a superlinear number of gradient queries. We close this gap for sufficiently large $n \gtrsim d^2 ε_{\text{dp}}^{-3}$, by using ReSQue to design an algorithm with near-linear gradient query complexity in this regime.

math.OC↗

arXiv2023

Moments, Random Walks, and Limits for Spectrum Approximation

We study lower bounds for the problem of approximating a one dimensional distribution given (noisy) measurements of its moments. We show that there are distributions on $[-1,1]$ that cannot be approximated to accuracy $ε$ in Wasserstein-1 distance even if we know \emph{all} of their moments to multiplicative accuracy $(1\pm2^{-Ω(1/ε)})$; this result matches an upper bound of Kong and Valiant [Annals of Statistics, 2017]. To obtain our result, we provide a hard instance involving distributions induced by the eigenvalue spectra of carefully constructed graph adjacency matrices. Efficiently approximating such spectra in Wasserstein-1 distance is a well-studied algorithmic problem, and a recent result of Cohen-Steiner et al. [KDD 2018] gives a method based on accurately approximating spectral moments using $2^{O(1/ε)}$ random walks initiated at uniformly random nodes in the graph. As a strengthening of our main result, we show that improving the dependence on $1/ε$ in this result would require a new algorithmic approach. Specifically, no algorithm can compute an $ε$-accurate approximation to the spectrum of a normalized graph adjacency matrix with constant probability, even when given the transcript of $2^{Ω(1/ε)}$ random walks of length $2^{Ω(1/ε)}$ started at random nodes.

cs.DS↗

arXiv2023

Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs Sampling

We give a quantum algorithm for computing an $ε$-approximate Nash equilibrium of a zero-sum game in a $m \times n$ payoff matrix with bounded entries. Given a standard quantum oracle for accessing the payoff matrix our algorithm runs in time $\widetilde{O}(\sqrt{m + n}\cdot ε^{-2.5} + ε^{-3})$ and outputs a classical representation of the $ε$-approximate Nash equilibrium. This improves upon the best prior quantum runtime of $\widetilde{O}(\sqrt{m + n} \cdot ε^{-3})$ obtained by [vAG19] and the classic $\widetilde{O}((m + n) \cdot ε^{-2})$ runtime due to [GK95] whenever $ε= Ω((m +n)^{-1})$. We obtain this result by designing new quantum data structures for efficiently sampling from a slowly-changing Gibbs distribution.

quant-ph↗

arXiv2022

VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation

We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q$-Learning (VO$Q$L), based on $Q$-learning and bound its regret assuming completeness and bounded Eluder dimension for the regression function class. As a special case, VO$Q$L achieves $\tilde{O}(d\sqrt{HT}+d^6H^{5})$ regret over $T$ episodes for a horizon $H$ MDP under ($d$-dimensional) linear function approximation, which is asymptotically optimal. Our algorithm incorporates weighted regression-based upper and lower bounds on the optimal value function to obtain this improved regret. The algorithm is computationally efficient given a regression oracle over the function class, making this the first computationally tractable and statistically optimal approach for linear MDPs.

cs.LG↗

arXiv2022

The Complexity of Infinite-Horizon General-Sum Stochastic Games

We study the complexity of computing stationary Nash equilibrium (NE) in n-player infinite-horizon general-sum stochastic games. We focus on the problem of computing NE in such stochastic games when each player is restricted to choosing a stationary policy and rewards are discounted. First, we prove that computing such NE is in PPAD (in addition to clearly being PPAD-hard). Second, we consider turn-based specializations of such games where at each state there is at most a single player that can take actions and show that these (seemingly-simpler) games remain PPAD-hard. Third, we show that under further structural assumptions on the rewards computing NE in such turn-based games is possible in polynomial time. Towards achieving these results we establish structural facts about stochastic games of broader utility, including monotonicity of utilities under single-state single-action changes and reductions to settings where each player controls a single state.

cs.GT↗

arXiv2022

Optimal and Adaptive Monteiro-Svaiter Acceleration

We develop a variant of the Monteiro-Svaiter (MS) acceleration framework that removes the need to solve an expensive implicit equation at every iteration. Consequently, for any $p\ge 2$ we improve the complexity of convex optimization with Lipschitz $p$th derivative by a logarithmic factor, matching a lower bound. We also introduce an MS subproblem solver that requires no knowledge of problem parameters, and implement it as either a second- or first-order method by solving linear systems or applying MinRes, respectively. On logistic regression our method outperforms previous second-order momentum methods, but under-performs Newton's method; simply iterating our first-order adaptive subproblem solver performs comparably to L-BFGS.

math.OC↗

arXiv2022

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

The accelerated proximal point algorithm (APPA), also known as "Catalyst", is a well-established reduction from convex optimization to approximate proximal point computation (i.e., regularized minimization). This reduction is conceptually elegant and yields strong convergence rate guarantees. However, these rates feature an extraneous logarithmic term arising from the need to compute each proximal point to high accuracy. In this work, we propose a novel Relaxed Error Criterion for Accelerated Proximal Point (RECAPP) that eliminates the need for high accuracy subproblem solutions. We apply RECAPP to two canonical problems: finite-sum and max-structured minimization. For finite-sum problems, we match the best known complexity, previously obtained by carefully-designed problem-specific algorithms. For minimizing $\max_y f(x,y)$ where $f$ is convex in $x$ and strongly-concave in $y$, we improve on the best known (Catalyst-based) bound by a logarithmic factor.

math.OC↗

arXiv2022

Regularized Box-Simplex Games and Dynamic Decremental Bipartite Matching

Box-simplex games are a family of bilinear minimax objectives which encapsulate graph-structured problems such as maximum flow [She17], optimal transport [JST19], and bipartite matching [AJJ+22]. We develop efficient near-linear time, high-accuracy solvers for regularized variants of these games. Beyond the immediate applications of such solvers for computing Sinkhorn distances, a prominent tool in machine learning, we show that these solvers can be used to obtain improved running times for maintaining a (fractional) $ε$-approximate maximum matching in a dynamic decremental bipartite graph against an adaptive adversary. We give a generic framework which reduces this dynamic matching problem to solving regularized graph-structured optimization problems to high accuracy. Through our reduction framework, our regularized box-simplex game solver implies a new algorithm for dynamic decremental bipartite matching in total time $\tilde{O}(m \cdot ε^{-3})$, from an initial graph with $m$ edges and $n$ nodes. We further show how to use recent advances in flow optimization [CKL+22] to improve our runtime to $m^{1 + o(1)} \cdot ε^{-2}$, thereby demonstrating the versatility of our reduction-based approach. These results improve upon the previous best runtime of $\tilde{O}(m \cdot ε^{-4})$ [BGS20] and illustrate the utility of using regularized optimization problem solvers for designing dynamic algorithms.

cs.DS↗

arXiv2022

Sharper Rates for Separable Minimax and Finite Sum Optimization via Primal-Dual Extragradient Methods

We design accelerated algorithms with improved rates for several fundamental classes of optimization problems. Our algorithms all build upon techniques related to the analysis of primal-dual extragradient methods via relative Lipschitzness proposed recently by [CST21]. (1) Separable minimax optimization. We study separable minimax optimization problems $\min_x \max_y f(x) - g(y) + h(x, y)$, where $f$ and $g$ have smoothness and strong convexity parameters $(L^x, μ^x)$, $(L^y, μ^y)$, and $h$ is convex-concave with a $(Λ^{xx}, Λ^{xy}, Λ^{yy})$-blockwise operator norm bounded Hessian. We provide an algorithm with gradient query complexity $\tilde{O}\left(\sqrt{\frac{L^{x}}{μ^{x}}} + \sqrt{\frac{L^{y}}{μ^{y}}} + \frac{Λ^{xx}}{μ^{x}} + \frac{Λ^{xy}}{\sqrt{μ^{x}μ^{y}}} + \frac{Λ^{yy}}{μ^{y}}\right)$. Notably, for convex-concave minimax problems with bilinear coupling (e.g.\ quadratics), where $Λ^{xx} = Λ^{yy} = 0$, our rate matches a lower bound of [ZHZ19]. (2) Finite sum optimization. We study finite sum optimization problems $\min_x \frac{1}{n}\sum_{i\in[n]} f_i(x)$, where each $f_i$ is $L_i$-smooth and the overall problem is $μ$-strongly convex. We provide an algorithm with gradient query complexity $\tilde{O}\left(n + \sum_{i\in[n]} \sqrt{\frac{L_i}{nμ}} \right)$. Notably, when the smoothness bounds $\{L_i\}_{i\in[n]}$ are non-uniform, our rate improves upon accelerated SVRG [LMH15, FGKS15] and Katyusha [All17] by up to a $\sqrt{n}$ factor. (3) Minimax finite sums. We generalize our algorithms for minimax and finite sum optimization to solve a natural family of minimax finite sum optimization problems at an accelerated rate, encapsulating both above results up to a logarithmic factor.

math.OC↗

arXiv2021

A Unified Framework for Multi-distribution Density Ratio Estimation

Binary density ratio estimation (DRE), the problem of estimating the ratio $p_1/p_2$ given their empirical samples, provides the foundation for many state-of-the-art machine learning algorithms such as contrastive representation learning and covariate shift adaptation. In this work, we consider a generalized setting where given samples from multiple distributions $p_1, \ldots, p_k$ (for $k > 2$), we aim to efficiently estimate the density ratios between all pairs of distributions. Such a generalization leads to important new applications such as estimating statistical discrepancy among multiple random variables like multi-distribution $f$-divergence, and bias correction via multiple importance sampling. We then develop a general framework from the perspective of Bregman divergence minimization, where each strictly convex multivariate function induces a proper loss for multi-distribution DRE. Moreover, we rederive the theoretical connection between multi-distribution density ratio estimation and class probability estimation, justifying the use of any strictly proper scoring rule composite with a link function for multi-distribution DRE. We show that our framework leads to methods that strictly generalize their counterparts in binary DRE, as well as new methods that show comparable or superior performance on various downstream tasks.

cs.LG↗

arXiv2021

Stochastic Bias-Reduced Gradient Methods

We develop a new primitive for stochastic optimization: a low-bias, low-cost estimator of the minimizer $x_\star$ of any Lipschitz strongly-convex function. In particular, we use a multilevel Monte-Carlo approach due to Blanchet and Glynn to turn any optimal stochastic gradient method into an estimator of $x_\star$ with bias $δ$, variance $O(\log(1/δ))$, and an expected sampling cost of $O(\log(1/δ))$ stochastic gradient evaluations. As an immediate consequence, we obtain cheap and nearly unbiased gradient estimators for the Moreau-Yoshida envelope of any Lipschitz convex function, allowing us to perform dimension-free randomized smoothing. We demonstrate the potential of our estimator through four applications. First, we develop a method for minimizing the maximum of $N$ functions, improving on recent results and matching a lower bound up to logarithmic factors. Second and third, we recover state-of-the-art rates for projection-efficient and gradient-efficient optimization using simple algorithms with a transparent analysis. Finally, we show that an improved version of our estimator would yield a nearly linear-time, optimal-utility, differentially-private non-smooth stochastic optimization method.

math.OC↗

arXiv2021

Semi-Streaming Bipartite Matching in Fewer Passes and Optimal Space

We provide $\widetilde{O}(ε^{-1})$-pass semi-streaming algorithms for computing $(1-ε)$-approximate maximum cardinality matchings in bipartite graphs. Our most efficient methods are deterministic and use optimal, $O(n)$, space, improving upon the space complexity of the previous state-of-the-art $\widetilde{O}(ε^{-1})$-pass algorithm of Ahn and Guha. To obtain our results we provide semi-streaming adaptations of more general continuous optimization tools. Further, we leverage these techniques to obtain improvements for streaming variants of approximate linear programming, optimal transport, exact matching, transshipment, and shortest path problems.

cs.DS↗

arXiv2021

Towards Tight Bounds on the Sample Complexity of Average-reward MDPs

We prove new upper and lower bounds for sample complexity of finding an $ε$-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model. When the mixing time of the probability transition matrix of all policies is at most $t_\mathrm{mix}$, we provide an algorithm that solves the problem using $\widetilde{O}(t_\mathrm{mix} ε^{-3})$ (oblivious) samples per state-action pair. Further, we provide a lower bound showing that a linear dependence on $t_\mathrm{mix}$ is necessary in the worst case for any algorithm which computes oblivious samples. We obtain our results by establishing connections between infinite-horizon average-reward MDPs and discounted MDPs of possible further utility.

cs.LG↗