arXiv subjects

Zhao Song

Publications and source records attributed to Zhao Song.

At least 253 records · Page 14Linked to original sources

arXiv2021

Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes

In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are constrained to use a single-pass over the data as well as sub-linear memory. The online setting has an additional requirement of maintaining a valid solution at any point in time. For solving these new problems, we propose algorithms with theoretical guarantees, evaluate them on several real-world datasets, and show that they give comparable performance to state-of-the-art offline algorithms that store the entire data in memory and take multiple passes over it.

cs.LG↗

arXiv2021

Approximation Algorithms for LCS and LIS with Truly Improved Running Times

Longest common subsequence ($\mathsf{LCS}$) is a classic and central problem in combinatorial optimization. While $\mathsf{LCS}$ admits a quadratic time solution, recent evidence suggests that solving the problem may be impossible in truly subquadratic time. A special case of $\mathsf{LCS}$ wherein each character appears at most once in every string is equivalent to the longest increasing subsequence problem ($\mathsf{LIS}$) which can be solved in quasilinear time. In this work, we present novel algorithms for approximating $\mathsf{LCS}$ in truly subquadratic time and $\mathsf{LIS}$ in truly sublinear time. Our approximation factors depend on the ratio of the optimal solution size over the input size. We denote this ratio by $λ$ and obtain the following results for $\mathsf{LCS}$ and $\mathsf{LIS}$ without any prior knowledge of $λ$. $\bullet$ A truly subquadratic time algorithm for $\mathsf{LCS}$ with approximation factor $Ω(λ^3)$. $\bullet$A truly sublinear time algorithm for $\mathsf{LIS}$ with approximation factor $Ω(λ^3)$. Triangle inequality was recently used by [Boroujeni, Ehsani, Ghodsi, HajiAghayi and Seddighin SODA 2018] and [Charkraborty, Das, Goldenberg, Koucky and Saks FOCS 2018] to present new approximation algorithms for edit distance. Our techniques for $\mathsf{LCS}$ extend the notion of triangle inequality to non-metric settings.

cs.DS↗

arXiv2021

Solving SDP Faster: A Robust IPM Framework and Efficient Implementation

This paper introduces a new robust interior point method analysis for semidefinite programming (SDP). This new robust analysis can be combined with either logarithmic barrier or hybrid barrier. Under this new framework, we can improve the running time of semidefinite programming (SDP) with variable size $n \times n$ and $m$ constraints up to $ε$ accuracy. We show that for the case $m = Ω(n^2)$, we can solve SDPs in $m^ω$ time. This suggests solving SDP is nearly as fast as solving the linear system with equal number of variables and constraints. This is the first result that tall dense SDP can be solved in the nearly-optimal running time, and it also improves the state-of-the-art SDP solver [Jiang, Kathuria, Lee, Padmanabhan and Song, FOCS 2020]. In addition to our new IPM analysis, we also propose a number of techniques that might be of further interest, such as, maintaining the inverse of a Kronecker product using lazy updates, a general amortization scheme for positive semidefinite matrices.

math.OC↗

arXiv2021

Scatterbrain: Unifying Sparse and Low-rank Attention Approximation

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is still challenging to balance the trade-off between model quality and efficiency to perform a one-size-fits-all approximation for different tasks. To better understand this trade-off, we observe that sparse and low-rank approximations excel in different regimes, determined by the softmax temperature in attention, and sparse + low-rank can outperform each individually. Inspired by the classical robust-PCA algorithm for sparse and low-rank decomposition, we propose Scatterbrain, a novel way to unify sparse (via locality sensitive hashing) and low-rank (via kernel feature map) attention for accurate and efficient approximation. The estimation is unbiased with provably low error. We empirically show that Scatterbrain can achieve 2.1x lower error than baselines when serving as a drop-in replacement in BigGAN image generation and pre-trained T2T-ViT. On a pre-trained T2T Vision transformer, even without fine-tuning, Scatterbrain can reduce 98% of attention memory at the cost of only 1% drop in accuracy. We demonstrate Scatterbrain for end-to-end training with up to 4 points better perplexity and 5 points better average accuracy than sparse or low-rank efficient transformers on language modeling and long-range-arena tasks.

cs.LG↗

arXiv2021

Bipartite Matching in Nearly-linear Time on Moderately Dense Graphs

We present an $\tilde O(m+n^{1.5})$-time randomized algorithm for maximum cardinality bipartite matching and related problems (e.g. transshipment, negative-weight shortest paths, and optimal transport) on $m$-edge, $n$-node graphs. For maximum cardinality bipartite matching on moderately dense graphs, i.e. $m = Ω(n^{1.5})$, our algorithm runs in time nearly linear in the input size and constitutes the first improvement over the classic $O(m\sqrt{n})$-time [Dinic 1970; Hopcroft-Karp 1971; Karzanov 1973] and $\tilde O(n^ω)$-time algorithms [Ibarra-Moran 1981; Mucha-Sankowski 2004] (where currently $ω\approx 2.373$). On sparser graphs, i.e. when $m = n^{9/8 + δ}$ for any constant $δ>0$, our result improves upon the recent advances of [Madry 2013] and [Liu-Sidford 2020b, 2020a] which achieve an $\tilde O(m^{4/3+o(1)})$ runtime. We obtain these results by combining and advancing recent lines of research in interior point methods (IPMs) and dynamic graph algorithms. First, we simplify and improve the IPM of [v.d.Brand-Lee-Sidford-Song 2020], providing a general primal-dual IPM framework and new sampling-based techniques for handling infeasibility induced by approximate linear system solvers. Second, we provide a simple sublinear-time algorithm for detecting and sampling high-energy edges in electric flows on expanders and show that when combined with recent advances in dynamic expander decompositions, this yields efficient data structures for maintaining the iterates of both [v.d.Brand et al.] and our new IPMs. Combining this general machinery yields a simpler $\tilde O(n \sqrt{m})$ time algorithm for matching based on the logarithmic barrier function, and our state-of-the-art $\tilde O(m+n^{1.5})$ time algorithm for matching based on the [Lee-Sidford 2014] barrier (as regularized in [v.d.Brand et al.]).

cs.DS↗

arXiv2021

Does Preprocessing Help Training Over-parameterized Neural Networks?

Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine learning. The classical training method requires paying $Ω(mnd)$ cost for both forward computation and backward computation, where $m$ is the width of the neural network, and we are given $n$ training points in $d$-dimensional space. In this paper, we propose two novel preprocessing ideas to bypass this $Ω(mnd)$ barrier: $\bullet$ First, by preprocessing the initial weights of the neural networks, we can train the neural network in $\widetilde{O}(m^{1-Θ(1/d)} n d)$ cost per iteration. $\bullet$ Second, by preprocessing the input data points, we can train the neural network in $\widetilde{O} (m^{4/5} nd )$ cost per iteration. From the technical perspective, our result is a sophisticated combination of tools in different fields, greedy-type convergence analysis in optimization, sparsity observation in practical work, high-dimensional geometric search in data structure, concentration and anti-concentration in probability. Our results also provide theoretical insights for a large number of previously established fast training methods. In addition, our classical algorithm can be generalized to the Quantum computation model. Interestingly, we can get a similar sublinear cost per iteration but avoid preprocessing initial weights or input data points.

cs.LG↗

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

Fast Sketching of Polynomial Kernels of Polynomial Degree

Kernel methods are fundamental in machine learning, and faster algorithms for kernel approximation provide direct speedups for many core tasks in machine learning. The polynomial kernel is especially important as other kernels can often be approximated by the polynomial kernel via a Taylor series expansion. Recent techniques in oblivious sketching reduce the dependence in the running time on the degree $q$ of the polynomial kernel from exponential to polynomial, which is useful for the Gaussian kernel, for which $q$ can be chosen to be polylogarithmic. However, for more slowly growing kernels, such as the neural tangent and arc-cosine kernels, $q$ needs to be polynomial, and previous work incurs a polynomial factor slowdown in the running time. We give a new oblivious sketch which greatly improves upon this running time, by removing the dependence on $q$ in the leading order term. Combined with a novel sampling scheme, we give the fastest algorithms for approximating a large family of slow-growing kernels.

cs.DS↗

arXiv2021

Metric Transforms and Low Rank Matrices via Representation Theory of the Real Hyperrectangle

In this paper, we develop a new technique which we call representation theory of the real hyperrectangle, which describes how to compute the eigenvectors and eigenvalues of certain matrices arising from hyperrectangles. We show that these matrices arise naturally when analyzing a number of different algorithmic tasks such as kernel methods, neural network training, natural language processing, and the design of algorithms using the polynomial method. We then use our new technique along with these connections to prove several new structural results in these areas, including: $\bullet$ A function is a positive definite Manhattan kernel if and only if it is a completely monotone function. These kernels are widely used across machine learning; one example is the Laplace kernel which is widely used in machine learning for chemistry. $\bullet$ A function transforms Manhattan distances to Manhattan distances if and only if it is a Bernstein function. This completes the theory of Manhattan to Manhattan metric transforms initiated by Assouad in 1980. $\bullet$ A function applied entry-wise to any square matrix of rank $r$ always results in a matrix of rank $< 2^{r-1}$ if and only if it is a polynomial of sufficiently low degree. This gives a converse to a key lemma used by the polynomial method in algorithm design. Our work includes a sophisticated combination of techniques from different fields, including metric embeddings, the polynomial method, and group representation theory.

cs.CG↗

arXiv2021

When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?

Particle filtering is a popular method for inferring latent states in stochastic dynamical systems, whose theoretical properties have been well studied in machine learning and statistics communities. In many control problems, e.g., partially observed linear dynamical systems (POLDS), oftentimes the inferred latent state is further used for planning at each step. This paper initiates a rigorous study on the efficiency of particle filtering for sequential planning, and gives the first particle complexity bounds. Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference. In particular, we show that, in stable systems, polynomially many particles suffice. Key in our proof is a coupling of the ideal sequence based on the exact planning and the sequence generated by approximate planning based on particle filtering. We believe this technique can be useful in other sequential decision-making problems.

cs.LG↗

arXiv2021

Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing

We present the first provable Least-Squares Value Iteration (LSVI) algorithms that have runtime complexity sublinear in the number of actions. We formulate the value function estimation procedure in value iteration as an approximate maximum inner product search problem and propose a locality sensitive hashing (LSH) [Indyk and Motwani STOC'98, Andoni and Razenshteyn STOC'15, Andoni, Laarhoven, Razenshteyn and Waingarten SODA'17] type data structure to solve this problem with sublinear time complexity. Moreover, we build the connections between the theory of approximate maximum inner product search and the regret analysis of reinforcement learning. We prove that, with our choice of approximation factor, our Sublinear LSVI algorithms maintain the same regret as the original LSVI algorithms while reducing the runtime complexity to sublinear in the number of actions. To the best of our knowledge, this is the first work that combines LSH with reinforcement learning resulting in provable improvements. We hope that our novel way of combining data-structures and iterative algorithm will open the door for further study into cost reduction in optimization.

cs.DS↗

arXiv2021

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

Federated Learning (FL) is an emerging learning scheme that allows different distributed clients to train deep neural networks together without data sharing. Neural networks have become popular due to their unprecedented success. To the best of our knowledge, the theoretical guarantees of FL concerning neural networks with explicit forms and multi-step updates are unexplored. Nevertheless, training analysis of neural networks in FL is non-trivial for two reasons: first, the objective loss function we are optimizing is non-smooth and non-convex, and second, we are even not updating in the gradient direction. Existing convergence results for gradient descent-based methods heavily rely on the fact that the gradient direction is used for updating. This paper presents a new class of convergence analysis for FL, Federated Learning Neural Tangent Kernel (FL-NTK), which corresponds to overparamterized ReLU neural networks trained by gradient descent in FL and is inspired by the analysis in Neural Tangent Kernel (NTK). Theoretically, FL-NTK converges to a global-optimal solution at a linear rate with properly tuned learning parameters. Furthermore, with proper distributional assumptions, FL-NTK can also achieve good generalization.

cs.LG↗

arXiv2021

On InstaHide, Phase Retrieval, and Sparse Matrix Factorization

In this work, we examine the security of InstaHide, a scheme recently proposed by [Huang, Song, Li and Arora, ICML'20] for preserving the security of private datasets in the context of distributed learning. To generate a synthetic training example to be shared among the distributed learners, InstaHide takes a convex combination of private feature vectors and randomly flips the sign of each entry of the resulting vector with probability 1/2. A salient question is whether this scheme is secure in any provable sense, perhaps under a plausible hardness assumption and assuming the distributions generating the public and private data satisfy certain properties. We show that the answer to this appears to be quite subtle and closely related to the average-case complexity of a new multi-task, missing-data version of the classic problem of phase retrieval. Motivated by this connection, we design a provable algorithm that can recover private vectors using only the public vectors and synthetic vectors generated by InstaHide, under the assumption that the private and public vectors are isotropic Gaussian.

cs.LG↗

arXiv2021

InstaHide: Instance-hiding Schemes for Private Distributed Learning

How can multiple distributed entities collaboratively train a shared deep net on their private data while preserving privacy? This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing distributed deep learning pipelines. The encryption is efficient and applying it during training has minor effect on test accuracy. InstaHide encrypts each training image with a "one-time secret key" which consists of mixing a number of randomly chosen images and applying a random pixel-wise mask. Other contributions of this paper include: (a) Using a large public dataset (e.g. ImageNet) for mixing during its encryption, which improves security. (b) Experimental results to show effectiveness in preserving privacy against known attacks with only minor effects on accuracy. (c) Theoretical analysis showing that successfully attacking privacy requires attackers to solve a difficult computational problem. (d) Demonstrating that use of the pixel-wise mask is important for security, since Mixup alone is shown to be insecure to some some efficient attacks. (e) Release of a challenge dataset https://github.com/Hazelsuko07/InstaHide_Challenge Our code is available at https://github.com/Hazelsuko07/InstaHide

cs.CR↗

arXiv2021

Near-Optimal Two-Pass Streaming Algorithm for Sampling Random Walks over Directed Graphs

For a directed graph $G$ with $n$ vertices and a start vertex $u_{\sf start}$, we wish to (approximately) sample an $L$-step random walk over $G$ starting from $u_{\sf start}$ with minimum space using an algorithm that only makes few passes over the edges of the graph. This problem found many applications, for instance, in approximating the PageRank of a webpage. If only a single pass is allowed, the space complexity of this problem was shown to be $\tildeΘ(n \cdot L)$. Prior to our work, a better space complexity was only known with $\tilde{O}(\sqrt{L})$ passes. We settle the space complexity of this random walk simulation problem for two-pass streaming algorithms, showing that it is $\tildeΘ(n \cdot \sqrt{L})$, by giving almost matching upper and lower bounds. Our lower bound argument extends to every constant number of passes $p$, and shows that any $p$-pass algorithm for this problem uses $\tildeΩ(n \cdot L^{1/p})$ space. In addition, we show a similar $\tildeΘ(n \cdot \sqrt{L})$ bound on the space complexity of any algorithm (with any number of passes) for the related problem of sampling an $L$-step random walk from every vertex in the graph.

cs.DS↗

arXiv2020

Training (Overparametrized) Neural Networks in Near-Linear Time

The slow convergence rate and pathological curvature issues of first-order gradient methods for training deep neural networks, initiated an ongoing effort for developing faster $\mathit{second}$-$\mathit{order}$ optimization algorithms beyond SGD, without compromising the generalization error. Despite their remarkable convergence rate ($\mathit{independent}$ of the training batch size $n$), second-order algorithms incur a daunting slowdown in the $\mathit{cost}$ $\mathit{per}$ $\mathit{iteration}$ (inverting the Hessian matrix of the loss function), which renders them impractical. Very recently, this computational overhead was mitigated by the works of [ZMG19,CGH+19}, yielding an $O(mn^2)$-time second-order algorithm for training two-layer overparametrized neural networks of polynomial width $m$. We show how to speed up the algorithm of [CGH+19], achieving an $\tilde{O}(mn)$-time backpropagation algorithm for training (mildly overparametrized) ReLU networks, which is near-linear in the dimension ($mn$) of the full gradient (Jacobian) matrix. The centerpiece of our algorithm is to reformulate the Gauss-Newton iteration as an $\ell_2$-regression problem, and then use a Fast-JL type dimension reduction to $\mathit{precondition}$ the underlying Gram matrix in time independent of $M$, allowing to find a sufficiently good approximate solution via $\mathit{first}$-$\mathit{order}$ conjugate gradient. Our result provides a proof-of-concept that advanced machinery from randomized linear algebra -- which led to recent breakthroughs in $\mathit{convex}$ $\mathit{optimization}$ (ERM, LPs, Regression) -- can be carried over to the realm of deep learning as well.

cs.LG↗

arXiv2020

Algorithms and Hardness for Linear Algebra on Geometric Graphs

For a function $\mathsf{K} : \mathbb{R}^{d} \times \mathbb{R}^{d} \to \mathbb{R}_{\geq 0}$, and a set $P = \{ x_1, \ldots, x_n\} \subset \mathbb{R}^d$ of $n$ points, the $\mathsf{K}$ graph $G_P$ of $P$ is the complete graph on $n$ nodes where the weight between nodes $i$ and $j$ is given by $\mathsf{K}(x_i, x_j)$. In this paper, we initiate the study of when efficient spectral graph theory is possible on these graphs. We investigate whether or not it is possible to solve the following problems in $n^{1+o(1)}$ time for a $\mathsf{K}$-graph $G_P$ when $d < n^{o(1)}$: $\bullet$ Multiply a given vector by the adjacency matrix or Laplacian matrix of $G_P$ $\bullet$ Find a spectral sparsifier of $G_P$ $\bullet$ Solve a Laplacian system in $G_P$'s Laplacian matrix For each of these problems, we consider all functions of the form $\mathsf{K}(u,v) = f(\|u-v\|_2^2)$ for a function $f:\mathbb{R} \rightarrow \mathbb{R}$. We provide algorithms and comparable hardness results for many such $\mathsf{K}$, including the Gaussian kernel, Neural tangent kernels, and more. For example, in dimension $d = Ω(\log n)$, we show that there is a parameter associated with the function $f$ for which low parameter values imply $n^{1+o(1)}$ time algorithms for all three of these problems and high parameter values imply the nonexistence of subquadratic time algorithms assuming Strong Exponential Time Hypothesis ($\mathsf{SETH}$), given natural assumptions on $f$. As part of our results, we also show that the exponential dependence on the dimension $d$ in the celebrated fast multipole method of Greengard and Rokhlin cannot be improved, assuming $\mathsf{SETH}$, for a broad class of functions $f$. To the best of our knowledge, this is the first formal limitation proven about fast multipole methods.

cs.DS↗