Searcharxiv⌕ Search

arXiv subjects

Yin Tat Lee

Publications and source records attributed to Yin Tat Lee.

At least 55 records · Page 3Linked to original sources
arXiv2021

Faster Maxflow via Improved Dynamic Spectral Vertex Sparsifiers

We make several advances broadly related to the maintenance of electrical flows in weighted graphs undergoing dynamic resistance updates, including: 1. More efficient dynamic spectral vertex sparsification, achieved by faster length estimation of random walks in weighted graphs using Morris counters [Morris 1978, Nelson-Yu 2020]. 2. A direct reduction from detecting edges with large energy in dynamic electric flows to dynamic spectral vertex sparsifiers. 3. A procedure for turning algorithms for estimating a sequence of vectors under updates from an oblivious adversary to one that tolerates adaptive adversaries via the Gaussian-mechanism from differential privacy. Combining these pieces with modifications to prior robust interior point frameworks gives an algorithm that on graphs with $m$ edges computes a mincost flow with edge costs and capacities in $[1, U]$ in time $\widetilde{O}(m^{3/2-1/58} \log^2 U)$. In prior and independent work, [Axiotis-Mądry-Vladu FOCS 2021] also obtained an improved algorithm for sparse mincost flows on capacitated graphs. Our algorithm implies a $\widetilde{O}(m^{3/2-1/58} \log U)$ time maxflow algorithm, improving over the $\widetilde{O}(m^{3/2-1/328}\log U)$ time maxflow algorithm of [Gao-Liu-Peng FOCS 2021].

cs.DS↗
arXiv2021

Computing Lewis Weights to High Precision

We present an algorithm for computing approximate $\ell_p$ Lewis weights to high precision. Given a full-rank $\mathbf{A} \in \mathbb{R}^{m \times n}$ with $m \geq n$ and a scalar $p>2$, our algorithm computes $ε$-approximate $\ell_p$ Lewis weights of $\mathbf{A}$ in $\widetilde{O}_p(\log(1/ε))$ iterations; the cost of each iteration is linear in the input size plus the cost of computing the leverage scores of $\mathbf{D}\mathbf{A}$ for diagonal $\mathbf{D} \in \mathbb{R}^{m \times m}$. Prior to our work, such a computational complexity was known only for $p \in (0, 4)$ [CohenPeng2015], and combined with this result, our work yields the first polylogarithmic-depth polynomial-work algorithm for the problem of computing $\ell_p$ Lewis weights to high precision for all constant $p > 0$. An important consequence of this result is also the first polylogarithmic-depth polynomial-work algorithm for computing a nearly optimal self-concordant barrier for a polytope.

cs.DS↗
arXiv2021

Numerical Composition of Differential Privacy

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP algorithms. The running time and memory needed for our algorithm to approximate the privacy curve of a DP algorithm composed with itself $k$ times is $\tilde{O}(\sqrt{k})$. This improves over the best prior method by Koskela et al. (2020) which requires $\tildeΩ(k^{1.5})$ running time. We demonstrate the utility of our algorithm by accurately computing the privacy loss of DP-SGD algorithm of Abadi et al. (2016) and showing that our algorithm speeds up the privacy computations by a few orders of magnitude compared to prior work, while maintaining similar accuracy.

cs.DS↗
arXiv2021

Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions

We give lower bounds on the performance of two of the most popular sampling methods in practice, the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator, when applied to well-conditioned distributions. Our main result is a nearly-tight lower bound of $\widetildeΩ(κd)$ on the mixing time of MALA from an exponentially warm start, matching a line of algorithmic results up to logarithmic factors and answering an open question of Chewi et. al. We also show that a polynomial dependence on dimension is necessary for the relaxation time of HMC under any number of leapfrog steps, and bound the gains achievable by changing the step count. Our HMC analysis draws upon a novel connection between leapfrog integration and Chebyshev polynomials, which may be of independent interest.

cs.DS↗
arXiv2021

Structured Logconcave Sampling with a Restricted Gaussian Oracle

We give algorithms for sampling several structured logconcave families to high accuracy. We further develop a reduction framework, inspired by proximal point methods in convex optimization, which bootstraps samplers for regularized densities to improve dependences on problem conditioning. A key ingredient in our framework is the notion of a "restricted Gaussian oracle" (RGO) for $g: \mathbb{R}^d \rightarrow \mathbb{R}$, which is a sampler for distributions whose negative log-likelihood sums a quadratic and $g$. By combining our reduction framework with our new samplers, we obtain the following bounds for sampling structured distributions to total variation distance $ε$. For composite densities $\exp(-f(x) - g(x))$, where $f$ has condition number $κ$ and convex (but possibly non-smooth) $g$ admits an RGO, we obtain a mixing time of $O(κd \log^3\frac{κd}ε)$, matching the state-of-the-art non-composite bound; no composite samplers with better mixing than general-purpose logconcave samplers were previously known. For logconcave finite sums $\exp(-F(x))$, where $F(x) = \frac{1}{n}\sum_{i \in [n]} f_i(x)$ has condition number $κ$, we give a sampler querying $\widetilde{O}(n + κ\max(d, \sqrt{nd}))$ gradient oracles to $\{f_i\}_{i \in [n]}$; no high-accuracy samplers with nontrivial gradient query complexity were previously known. For densities with condition number $κ$, we give an algorithm obtaining mixing time $O(κd \log^2\frac{κd}ε)$, improving the prior state-of-the-art by a logarithmic factor with a significantly simpler analysis; we also show a zeroth-order algorithm attains the same query complexity.

cs.DS↗
arXiv2021

Solving Tall Dense Linear Programs in Nearly Linear Time

In this paper we provide an $\tilde{O}(nd+d^{3})$ time randomized algorithm for solving linear programs with $d$ variables and $n$ constraints with high probability. To obtain this result we provide a robust, primal-dual $\tilde{O}(\sqrt{d})$-iteration interior point method inspired by the methods of Lee and Sidford (2014, 2019) and show how to efficiently implement this method using new data-structures based on heavy-hitters, the Johnson-Lindenstrauss lemma, and inverse maintenance. Interestingly, we obtain this running time without using fast matrix multiplication and consequently, barring a major advance in linear system solving, our running time is near optimal for solving dense linear programs among algorithms that do not use fast matrix multiplication.

cs.DS↗
arXiv2021

Minimum Cost Flows, MDPs, and $\ell_1$-Regression in Nearly Linear Time for Dense Instances

In this paper we provide new randomized algorithms with improved runtimes for solving linear programs with two-sided constraints. In the special case of the minimum cost flow problem on $n$-vertex $m$-edge graphs with integer polynomially-bounded costs and capacities we obtain a randomized method which solves the problem in $\tilde{O}(m+n^{1.5})$ time. This improves upon the previous best runtime of $\tilde{O}(m\sqrt{n})$ (Lee-Sidford 2014) and, in the special case of unit-capacity maximum flow, improves upon the previous best runtimes of $m^{4/3+o(1)}$ (Liu-Sidford 2020, Kathuria 2020) and $\tilde{O}(m\sqrt{n})$ (Lee-Sidford 2014) for sufficiently dense graphs. For $\ell_1$-regression in a matrix with $n$-columns and $m$-rows we obtain a randomized method which computes an $ε$-approximate solution in $\tilde{O}(mn+n^{2.5})$ time. This yields a randomized method which computes an $ε$-optimal policy of a discounted Markov Decision Process with $S$ states and $A$ actions per state in time $\tilde{O}(S^2A+S^{2.5})$. These methods improve upon the previous best runtimes of methods which depend polylogarithmically on problem parameters, which were $\tilde{O}(mn^{1.5})$ (Lee-Sidford 2015) and $\tilde{O}(S^{2.5}A)$ (Lee-Sidford 2014, Sidford-Wang-Wu-Ye 2018). To obtain this result we introduce two new algorithmic tools of independent interest. First, we design a new general interior point method for solving linear programs with two sided constraints which combines techniques from (Lee-Song-Zhang 2019, Brand et al. 2020) to obtain a robust stochastic method with iteration count nearly the square root of the smaller dimension. Second, to implement this method we provide dynamic data structures for efficiently maintaining approximations to variants of Lewis-weights, a fundamental importance measure for matrices which generalize leverage scores and effective resistances.

cs.DS↗
arXiv2021

Chasing Nested Convex Bodies Nearly Optimally

The convex body chasing problem, introduced by Friedman and Linial, is a competitive analysis problem on any normed vector space. In convex body chasing, for each timestep $t\in\mathbb N$, a convex body $K_t\subseteq \mathbb R^d$ is given as a request, and the player picks a point $x_t\in K_t$. The player aims to ensure that the total distance $\sum_{t=0}^{T-1}||x_t-x_{t+1}||$ is within a bounded ratio of the smallest possible offline solution. In this work, we consider the nested version of the problem, in which the sequence $(K_t)$ must be decreasing. For Euclidean spaces, we consider a memoryless algorithm which moves to the so-called Steiner point, and show that in a certain sense it is exactly optimal among memoryless algorithms. For general finite dimensional normed spaces, we combine the Steiner point and our recent previous algorithm to obtain a new algorithm which is nearly optimal for all $\ell^p_d$ spaces with $p\geq 1$, closing a polynomial gap.

cs.DS↗
arXiv2021

Positive Semidefinite Programming: Mixed, Parallel, and Width-Independent

We give the first approximation algorithm for mixed packing and covering semidefinite programs (SDPs) with polylogarithmic dependence on width. Mixed packing and covering SDPs constitute a fundamental algorithmic primitive with recent applications in combinatorial optimization, robust learning, and quantum complexity. The current approximate solvers for positive semidefinite programming can handle only pure packing instances, and technical hurdles prevent their generalization to a wider class of positive instances. For a given multiplicative accuracy of $ε$, our algorithm takes $O(\log^3(ndρ) \cdot ε^{-3})$ parallelizable iterations, where $n$, $d$ are dimensions of the problem and $ρ$ is a width parameter of the instance, generalizing or improving all previous parallel algorithms in the positive linear and semidefinite programming literature. When specialized to pure packing SDPs, our algorithm's iteration complexity is $O(\log^2 (nd) \cdot ε^{-2})$, a slight improvement and derandomization of the state-of-the-art (Allen-Zhu et. al. '16, Peng et. al. '16, Wang et. al. '15). For a wide variety of structured instances commonly found in applications, the iterations of our algorithm run in nearly-linear time. In doing so, we give matrix analytic techniques for overcoming obstacles that have stymied prior approaches to this open problem, as stated in past works (Peng et. al. '16, Mahoney et. al. '16). Crucial to our analysis are a simplification of existing algorithms for mixed positive linear programs, achieved by removing an asymmetry caused by modifying covering constraints, and a suite of matrix inequalities whose proofs are based on analyzing the Schur complements of matrices in a higher dimension. We hope that both our algorithm and techniques open the door to improved solvers for positive semidefinite programming, as well as its applications.

cs.DS↗
arXiv2021

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. We get a (nearly) optimal bound on the excess empirical risk and excess population loss with subquadratic gradient complexity. More precisely, our differentially private algorithm requires $O(\frac{N^{3/2}}{d^{1/8}}+ \frac{N^2}{d})$ gradient queries for optimal excess empirical risk, which is achieved with the help of subsampling and smoothing the function via convolution. This is the first subquadratic algorithm for the non-smooth case when $d$ is super constant. As a direct application, using the iterative localization approach of Feldman et al. \cite{fkt20}, we achieve the optimal excess population loss for stochastic convex optimization problem, with $O(\min\{N^{5/4}d^{1/8},\frac{ N^{3/2}}{d^{1/8}}\})$ gradient queries. Our work makes progress towards resolving a question raised by Bassily et al. \cite{bfgt20}, giving first algorithms for private ERM and SCO with subquadratic steps. We note that independently Asi et al. \cite{afkt21} gave other algorithms for private ERM and SCO with subquadratic steps.

cs.LG↗
arXiv2021

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is extremely slow and memory intensive in practice. In this paper, we present a new framework to design differentially private optimizers called DP-SGD-JL and DP-Adam-JL. Our approach uses Johnson-Lindenstrauss (JL) projections to quickly approximate the per-sample gradient norms without exactly computing them, thus making the training time and memory requirements of our optimizers closer to that of their non-DP versions. Unlike previous attempts to make DP-SGD faster which work only on a subset of network architectures or use compiler techniques, we propose an algorithmic solution which works for any network in a black-box manner which is the main contribution of this paper. To illustrate this, on IMDb dataset, we train a Recurrent Neural Network (RNN) to achieve good privacy-vs-accuracy tradeoff, while being significantly faster than DP-SGD and with a similar memory footprint as non-private SGD. The privacy analysis of our algorithms is more involved than DP-SGD, we use the recently proposed f-DP framework of Dong et al. (2019) to prove privacy.

cs.LG↗
arXiv2021

Complexity of Highly Parallel Non-Smooth Convex Optimization

A landmark result of non-smooth convex optimization is that gradient descent is an optimal algorithm whenever the number of computed gradients is smaller than the dimension $d$. In this paper we study the extension of this result to the parallel optimization setting. Namely we consider optimization algorithms interacting with a highly parallel gradient oracle, that is one that can answer $\mathrm{poly}(d)$ gradient queries in parallel. We show that in this case gradient descent is optimal only up to $\tilde{O}(\sqrt{d})$ rounds of interactions with the oracle. The lower bound improves upon a decades old construction by Nemirovski which proves optimality only up to $d^{1/3}$ rounds (as recently observed by Balkanski and Singer), and the suboptimality of gradient descent after $\sqrt{d}$ rounds was already observed by Duchi, Bartlett and Wainwright. In the latter regime we propose a new method with improved complexity, which we conjecture to be optimal. The analysis of this new method is based upon a generalized version of the recent results on optimal acceleration for highly smooth convex optimization.

math.OC↗
arXiv2020

Metrical task systems on trees via mirror descent and unfair gluing

We consider metrical task systems on tree metrics, and present an $O(\mathrm{depth} \times \log n)$-competitive randomized algorithm based on the mirror descent framework introduced in our prior work on the $k$-server problem. For the special case of hierarchically separated trees (HSTs), we use mirror descent to refine the standard approach based on gluing unfair metrical task systems. This yields an $O(\log n)$-competitive algorithm for HSTs, thus removing an extraneous $\log\log n$ in the bound of Fiat and Mendel (2003). Combined with well-known HST embedding theorems, this also gives an $O((\log n)^2)$-competitive randomized algorithm for every $n$-point metric space.

cs.DS↗
arXiv2020

Network size and weights size for memorization with two-layers neural networks

In 1988, Eric B. Baum showed that two-layers neural networks with threshold activation function can perfectly memorize the binary labels of $n$ points in general position in $\mathbb{R}^d$ using only $\ulcorner n/d \urcorner$ neurons. We observe that with ReLU networks, using four times as many neurons one can fit arbitrary real labels. Moreover, for approximate memorization up to error $ε$, the neural tangent kernel can also memorize with only $O\left(\frac{n}{d} \cdot \log(1/ε) \right)$ neurons (assuming that the data is well dispersed too). We show however that these constructions give rise to networks where the magnitude of the neurons' weights are far from optimal. In contrast we propose a new training procedure for ReLU networks, based on complex (as opposed to real) recombination of the neurons, for which we show approximate memorization with both $O\left(\frac{n}{d} \cdot \frac{\log(1/ε)}ε\right)$ neurons, as well as nearly-optimal size of the weights.

cs.LG↗
arXiv2020

Solving Linear Programs in the Current Matrix Multiplication Time

This paper shows how to solve linear programs of the form $\min_{Ax=b,x\geq0} c^\top x$ with $n$ variables in time $$O^*((n^ω+n^{2.5-α/2}+n^{2+1/6}) \log(n/δ))$$ where $ω$ is the exponent of matrix multiplication, $α$ is the dual exponent of matrix multiplication, and $δ$ is the relative accuracy. For the current value of $ω\sim2.37$ and $α\sim0.31$, our algorithm takes $O^*(n^ω \log(n/δ))$ time. When $ω= 2$, our algorithm takes $O^*(n^{2+1/6} \log(n/δ))$ time. Our algorithm utilizes several new concepts that we believe may be of independent interest: $\bullet$ We define a stochastic central path method. $\bullet$ We show how to maintain a projection matrix $\sqrt{W}A^{\top}(AWA^{\top})^{-1}A\sqrt{W}$ in sub-quadratic time under $\ell_{2}$ multiplicative changes in the diagonal matrix $W$.

cs.DS↗
arXiv2020

A Faster Interior Point Method for Semidefinite Programming

Semidefinite programs (SDPs) are a fundamental class of optimization problems with important recent applications in approximation algorithms, quantum complexity, robust learning, algorithmic rounding, and adversarial deep learning. This paper presents a faster interior point method to solve generic SDPs with variable size $n \times n$ and $m$ constraints in time \begin{align*} \widetilde{O}(\sqrt{n}( mn^2 + m^ω+ n^ω) \log(1 / ε) ), \end{align*} where $ω$ is the exponent of matrix multiplication and $ε$ is the relative accuracy. In the predominant case of $m \geq n$, our runtime outperforms that of the previous fastest SDP solver, which is based on the cutting plane method of Jiang, Lee, Song, and Wong [JLSW20]. Our algorithm's runtime can be naturally interpreted as follows: $\widetilde{O}(\sqrt{n} \log (1/ε))$ is the number of iterations needed for our interior point method, $mn^2$ is the input size, and $m^ω+ n^ω$ is the time to invert the Hessian and slack matrix in each iteration. These constitute natural barriers to further improving the runtime of interior point methods for solving generic SDPs.

cs.DS↗
arXiv2020

Solving Linear Programs with Sqrt(rank) Linear System Solves

We present an algorithm that given a linear program with $n$ variables, $m$ constraints, and constraint matrix $A$, computes an $ε$-approximate solution in $\tilde{O}(\sqrt{rank(A)}\log(1/ε))$ iterations with high probability. Each iteration of our method consists of solving $\tilde{O}(1)$ linear systems and additional nearly linear time computation, improving by a factor of $\tildeΩ((m/rank(A))^{1/2})$ over the previous fastest method with this iteration cost due to Renegar (1988). Further, we provide a deterministic polynomial time computable $\tilde{O}(rank(A))$-self-concordant barrier function for the polytope, resolving an open question of Nesterov and Nemirovski (1994) on the theory of "universal barriers" for interior point methods. Applying our techniques to the linear program formulation of maximum flow yields an $\tilde{O}(|E|\sqrt{|V|}\log(U))$ time algorithm for solving the maximum flow problem on directed graphs with $|E|$ edges, $|V|$ vertices, and integer capacities of size at most $U$. This improves upon the previous fastest polynomial running time of $O(|E|\min\{|E|^{1/2},|V|^{2/3}\}\log(|V|^{2}/|E|)\log(U))$ achieved by Goldberg and Rao (1998). In the special case of solving dense directed unit capacity graphs our algorithm improves upon the previous fastest running times of $O(|E|\min\{|E|^{1/2},|V|^{2/3}\})$ achieved by Even and Tarjan (1975) and Karzanov (1973) and of $\tilde{O}(|E|^{10/7})$ achieved more recently by Mądry (2013).

cs.DS↗