arXiv subjects

Li-Yang Tan

Publications and source records attributed to Li-Yang Tan.

At least 55 records · Page 3Linked to original sources

arXiv2020

Provable guarantees for decision tree induction: the agnostic setting

We give strengthened provable guarantees on the performance of widely employed and empirically successful {\sl top-down decision tree learning heuristics}. While prior works have focused on the realizable setting, we consider the more realistic and challenging {\sl agnostic} setting. We show that for all monotone functions~$f$ and parameters $s\in \mathbb{N}$, these heuristics construct a decision tree of size $s^{\tilde{O}((\log s)/\varepsilon^2)}$ that achieves error $\le \mathsf{opt}_s + \varepsilon$, where $\mathsf{opt}_s$ denotes the error of the optimal size-$s$ decision tree for $f$. Previously, such a guarantee was not known to be achievable by any algorithm, even one that is not based on top-down heuristics. We complement our algorithmic guarantee with a near-matching $s^{\tildeΩ(\log s)}$ lower bound.

cs.DS↗

arXiv2020

The Power of Many Samples in Query Complexity

The randomized query complexity $R(f)$ of a boolean function $f\colon\{0,1\}^n\to\{0,1\}$ is famously characterized (via Yao's minimax) by the least number of queries needed to distinguish a distribution $D_0$ over $0$-inputs from a distribution $D_1$ over $1$-inputs, maximized over all pairs $(D_0,D_1)$. We ask: Does this task become easier if we allow query access to infinitely many samples from either $D_0$ or $D_1$? We show the answer is no: There exists a hard pair $(D_0,D_1)$ such that distinguishing $D_0^\infty$ from $D_1^\infty$ requires $Θ(R(f))$ many queries. As an application, we show that for any composed function $f\circ g$ we have $R(f\circ g) \geq Ω(\mathrm{fbs}(f)R(g))$ where $\mathrm{fbs}$ denotes fractional block sensitivity.

cs.CC↗

arXiv2020

New lower bounds for Massively Parallel Computation from query complexity

Roughgarden, Vassilvitskii, and Wang (JACM 18) recently introduced a novel framework for proving lower bounds for Massively Parallel Computation using techniques from boolean function complexity. We extend their framework in two different ways, to capture two common features of Massively Parallel Computation: $\circ$ Adaptivity, where machines can write to and adaptively read from shared memory throughout the execution of the computation. Recent work of Behnezhad et al. (SPAA 19) showed that adaptivity enables significantly improved round complexities for a number of central graph problems. $\circ$ Promise problems, where the algorithm only has to succeed on certain inputs. These inputs may have special structure that is of particular interest, or they may be representative of hard instances of the overall problem. Using this extended framework, we give the first unconditional lower bounds on the complexity of distinguishing whether an input graph is a cycle of length $n$ or two cycles of length $n/2$. This promise problem, 1v2-Cycle, has emerged as a central problem in the study of Massively Parallel Computation. We prove that any adaptive algorithm for the 1v2-Cycle problem with I/O capacity $O(n^{\varepsilon})$ per machine requires $Ω(1/\varepsilon)$ rounds, matching a recent upper bound of Behnezhad et al. In addition to strengthening the connections between Massively Parallel Computation and boolean function complexity, we also develop new machinery to reason about the latter. At the heart of our proofs are optimal lower bounds on the query complexity and approximate certificate complexity of the 1v2-Cycle problem.

cs.DS↗

arXiv2019

Constructive derandomization of query algorithms

We give efficient deterministic algorithms for converting randomized query algorithms into deterministic ones. We first give an algorithm that takes as input a randomized $q$-query algorithm $R$ with description length $N$ and a parameter $\varepsilon$, runs in time $\mathrm{poly}(N) \cdot 2^{O(q/\varepsilon)}$, and returns a deterministic $O(q/\varepsilon)$-query algorithm $D$ that $\varepsilon$-approximates the acceptance probabilities of $R$. These parameters are near-optimal: runtime $N + 2^{Ω(q/\varepsilon)}$ and query complexity $Ω(q/\varepsilon)$ are necessary. Next, we give algorithms for instance-optimal and online versions of the problem: $\circ$ Instance optimal: Construct a deterministic $q^\star_R$-query algorithm $D$, where $q^\star_R$ is minimum query complexity of any deterministic algorithm that $\varepsilon$-approximates $R$. $\circ$ Online: Deterministically approximate the acceptance probability of $R$ for a specific input $\underline{x}$ in time $\mathrm{poly}(N,q,1/\varepsilon)$, without constructing $D$ in its entirety. Applying the techniques we develop for these extensions, we constructivize classic results that relate the deterministic, randomized, and quantum query complexities of boolean functions (Nisan, STOC 1989; Beals et al., FOCS 1998). This has direct implications for the Turing machine model of computation: sublinear-time algorithms for total decision problems can be efficiently derandomized and dequantized with a subexponential-time preprocessing step.

cs.CC↗

arXiv2019

Top-down induction of decision trees: rigorous guarantees and inherent limitations

Consider the following heuristic for building a decision tree for a function $f : \{0,1\}^n \to \{\pm 1\}$. Place the most influential variable $x_i$ of $f$ at the root, and recurse on the subfunctions $f_{x_i=0}$ and $f_{x_i=1}$ on the left and right subtrees respectively; terminate once the tree is an $\varepsilon$-approximation of $f$. We analyze the quality of this heuristic, obtaining near-matching upper and lower bounds: $\circ$ Upper bound: For every $f$ with decision tree size $s$ and every $\varepsilon \in (0,\frac1{2})$, this heuristic builds a decision tree of size at most $s^{O(\log(s/\varepsilon)\log(1/\varepsilon))}$. $\circ$ Lower bound: For every $\varepsilon \in (0,\frac1{2})$ and $s \le 2^{\tilde{O}(\sqrt{n})}$, there is an $f$ with decision tree size $s$ such that this heuristic builds a decision tree of size $s^{\tildeΩ(\log s)}$. We also obtain upper and lower bounds for monotone functions: $s^{O(\sqrt{\log s}/\varepsilon)}$ and $s^{\tildeΩ(\sqrt[4]{\log s } )}$ respectively. The lower bound disproves conjectures of Fiat and Pechyony (2004) and Lee (2009). Our upper bounds yield new algorithms for properly learning decision trees under the uniform distribution. We show that these algorithms---which are motivated by widely employed and empirically successful top-down decision tree learning heuristics such as ID3, C4.5, and CART---achieve provable guarantees that compare favorably with those of the current fastest algorithm (Ehrenfeucht and Haussler, 1989). Our lower bounds shed new light on the limitations of these heuristics. Finally, we revisit the classic work of Ehrenfeucht and Haussler. We extend it to give the first uniform-distribution proper learning algorithm that achieves polynomial sample and memory complexity, while matching its state-of-the-art quasipolynomial runtime.

cs.DS↗

arXiv2018

Fooling Polytopes

We give a pseudorandom generator that fools $m$-facet polytopes over $\{0,1\}^n$ with seed length $\mathrm{polylog}(m) \cdot \log n$. The previous best seed length had superlinear dependence on $m$. An immediate consequence is a deterministic quasipolynomial time algorithm for approximating the number of solutions to any $\{0,1\}$-integer program.

cs.CC↗

arXiv2018

Luby--Veličković--Wigderson revisited: Improved correlation bounds and pseudorandom generators for depth-two circuits

We study correlation bounds and pseudorandom generators for depth-two circuits that consist of a $\mathsf{SYM}$-gate (computing an arbitrary symmetric function) or $\mathsf{THR}$-gate (computing an arbitrary linear threshold function) that is fed by $S$ $\mathsf{AND}$ gates. Such circuits were considered in early influential work on unconditional derandomization of Luby, Veličković, and Wigderson [LVW93], who gave the first non-trivial PRG with seed length $2^{O(\sqrt{\log(S/\varepsilon)})}$ that $\varepsilon$-fools these circuits. In this work we obtain the first strict improvement of [LVW93]'s seed length: we construct a PRG that $\varepsilon$-fools size-$S$ $\{\mathsf{SYM},\mathsf{THR}\} \circ\mathsf{AND}$ circuits over $\{0,1\}^n$ with seed length \[ 2^{O(\sqrt{\log S })} + \mathrm{polylog}(1/\varepsilon), \] an exponential (and near-optimal) improvement of the $\varepsilon$-dependence of [LVW93]. The above PRG is actually a special case of a more general PRG which we establish for constant-depth circuits containing multiple $\mathsf{SYM}$ or $\mathsf{THR}$ gates, including as a special case $\{\mathsf{SYM},\mathsf{THR}\} \circ \mathsf{AC^0}$ circuits. These more general results strengthen previous results of Viola [Vio06] and essentially strengthen more recent results of Lovett and Srinivasan [LS11]. Our improved PRGs follow from improved correlation bounds, which are transformed into PRGs via the Nisan--Wigderson "hardness versus randomness" paradigm [NW94]. The key to our improved correlation bounds is the use of a recent powerful \emph{multi-switching} lemma due to Håstad [Hås14].

cs.CC↗

arXiv2018

Non-Malleable Codes for Small-Depth Circuits

We construct efficient, unconditional non-malleable codes that are secure against tampering functions computed by small-depth circuits. For constant-depth circuits of polynomial size (i.e. $\mathsf{AC^0}$ tampering functions), our codes have codeword length $n = k^{1+o(1)}$ for a $k$-bit message. This is an exponential improvement of the previous best construction due to Chattopadhyay and Li (STOC 2017), which had codeword length $2^{O(\sqrt{k})}$. Our construction remains efficient for circuit depths as large as $Θ(\log(n)/\log\log(n))$ (indeed, our codeword length remains $n\leq k^{1+ε})$, and extending our result beyond this would require separating $\mathsf{P}$ from $\mathsf{NC^1}$. We obtain our codes via a new efficient non-malleable reduction from small-depth tampering to split-state tampering. A novel aspect of our work is the incorporation of techniques from unconditional derandomization into the framework of non-malleable reductions. In particular, a key ingredient in our analysis is a recent pseudorandom switching lemma of Trevisan and Xue (CCC 2013), a derandomization of the influential switching lemma from circuit complexity; the randomness-efficiency of this switching lemma translates into the rate-efficiency of our codes via our non-malleable reduction.

cs.CC↗

arXiv2018

Deterministic search for CNF satisfying assignments in almost polynomial time

We consider the fundamental derandomization problem of deterministically finding a satisfying assignment to a CNF formula that has many satisfying assignments. We give a deterministic algorithm which, given an $n$-variable $\mathrm{poly}(n)$-clause CNF formula $F$ that has at least $\varepsilon 2^n$ satisfying assignments, runs in time \[ n^{\tilde{O}(\log\log n)^2} \] for $\varepsilon \ge 1/\mathrm{polylog}(n)$ and outputs a satisfying assignment of $F$. Prior to our work the fastest known algorithm for this problem was simply to enumerate over all seeds of a pseudorandom generator for CNFs; using the best known PRGs for CNFs [DETT10], this takes time $n^{\tildeΩ(\log n)}$ even for constant $\varepsilon$. Our approach is based on a new general framework relating deterministic search and deterministic approximate counting, which we believe may find further applications.

cs.CC↗

arXiv2018

Improved pseudorandom generators from pseudorandom multi-switching lemmas

We give the best known pseudorandom generators for two touchstone classes in unconditional derandomization: an $\varepsilon$-PRG for the class of size-$M$ depth-$d$ $\mathsf{AC}^0$ circuits with seed length $\log(M)^{d+O(1)}\cdot \log(1/\varepsilon)$, and an $\varepsilon$-PRG for the class of $S$-sparse $\mathbb{F}_2$ polynomials with seed length $2^{O(\sqrt{\log S})}\cdot \log(1/\varepsilon)$. These results bring the state of the art for unconditional derandomization of these classes into sharp alignment with the state of the art for computational hardness for all parameter settings: improving on the seed lengths of either PRG would require breakthrough progress on longstanding and notorious circuit lower bounds. The key enabling ingredient in our approach is a new \emph{pseudorandom multi-switching lemma}. We derandomize recently-developed \emph{multi}-switching lemmas, which are powerful generalizations of Håstad's switching lemma that deal with \emph{families} of depth-two circuits. Our pseudorandom multi-switching lemma---a randomness-efficient algorithm for sampling restrictions that simultaneously simplify all circuits in a family---achieves the parameters obtained by the (full randomness) multi-switching lemmas of Impagliazzo, Matthews, and Paturi [IMP12] and Håstad [Hås14]. This optimality of our derandomization translates into the optimality (given current circuit lower bounds) of our PRGs for $\mathsf{AC}^0$ and sparse $\mathbb{F}_2$ polynomials.

cs.CC↗

arXiv2017

Adaptivity is exponentially powerful for testing monotonicity of halfspaces

We give a $\mathrm{poly}(\log n, 1/ε)$-query adaptive algorithm for testing whether an unknown Boolean function $f: \{-1,1\}^n \to \{-1,1\}$, which is promised to be a halfspace, is monotone versus $ε$-far from monotone. Since non-adaptive algorithms are known to require almost $Ω(n^{1/2})$ queries to test whether an unknown halfspace is monotone versus far from monotone, this shows that adaptivity enables an exponential improvement in the query complexity of monotonicity testing for halfspaces.

cs.CC↗

arXiv2017

Settling the query complexity of non-adaptive junta testing

We prove that any non-adaptive algorithm that tests whether an unknown Boolean function $f: \{0, 1\}^n\to \{0, 1\}$ is a $k$-junta or $ε$-far from every $k$-junta must make $\widetildeΩ(k^{3/2} / ε)$ many queries for a wide range of parameters $k$ and $ε$. Our result dramatically improves previous lower bounds from [BGSMdW13, STW15], and is essentially optimal given Blais's non-adaptive junta tester from [Blais08], which makes $\widetilde{O}(k^{3/2})/ε$ queries. Combined with the adaptive tester of [Blais09] which makes $O(k\log k + k /ε)$ queries, our result shows that adaptivity enables polynomial savings in query complexity for junta testing.

cs.CC↗

arXiv2017

Fooling intersections of low-weight halfspaces

A weight-$t$ halfspace is a Boolean function $f(x)=$sign$(w_1 x_1 + \cdots + w_n x_n - θ)$ where each $w_i$ is an integer in $\{-t,\dots,t\}.$ We give an explicit pseudorandom generator that $δ$-fools any intersection of $k$ weight-$t$ halfspaces with seed length poly$(\log n, \log k,t,1/δ)$. In particular, our result gives an explicit PRG that fools any intersection of any quasipoly$(n)$ number of halfspaces of any poly$\log(n)$ weight to any $1/$poly$\log(n)$ accuracy using seed length poly$\log(n).$ Prior to this work no explicit PRG with non-trivial seed length was known even for fooling intersections of $n$ weight-1 halfspaces to constant accuracy. The analysis of our PRG fuses techniques from two different lines of work on unconditional pseudorandomness for different kinds of Boolean functions. We extend the approach of Harsha, Klivans and Meka \cite{HKM12} for fooling intersections of regular halfspaces, and combine this approach with results of Bazzi \cite{Bazzi:07} and Razborov \cite{Razborov:09} on bounded independence fooling CNF formulas. Our analysis introduces new coupling-based ingredients into the standard Lindeberg method for establishing quantitative central limit theorems and associated pseudorandomness results.

cs.CC↗

arXiv2016

Hypercontractive inequalities via SOS, and the Frankl--Rödl graph

Our main result is a formulation and proof of the reverse hypercontractive inequality in the sum-of-squares (SOS) proof system. As a consequence we show that for any constant $0 < γ\leq 1/4$, the SOS/Lasserre SDP hierarchy at degree $4\lceil \frac{1}{4γ}\rceil$ certifies the statement "the maximum independent set in the Frankl--Rödl graph $\mathrm{FR}^{n}_γ$ has fractional size~$o(1)$". Here $\mathrm{FR}^{n}_γ = (V,E)$ is the graph with $V = \{0,1\}^n$ and $(x,y) \in E$ whenever $Δ(x,y) = (1-γ)n$ (an even integer). In particular, we show the degree-$4$ SOS algorithm certifies the chromatic number lower bound "$χ(\mathrm{FR}^{n}_{1/4}) = ω(1)$", even though $\mathrm{FR}^{n}_{1/4}$ is the canonical integrality gap instance for which standard SDP relaxations cannot even certify "$χ(\mathrm{FR}^{n}_{1/4}) > 3$". Finally, we also give an SOS proof of (a generalization of) the sharp $(2,q)$-hypercontractive inequality for any even integer $q$.

cs.CC↗

arXiv2015

Near-optimal small-depth lower bounds for small distance connectivity

We show that any depth-$d$ circuit for determining whether an $n$-node graph has an $s$-to-$t$ path of length at most $k$ must have size $n^{Ω(k^{1/d}/d)}$. The previous best circuit size lower bounds for this problem were $n^{k^{\exp(-O(d))}}$ (due to Beame, Impagliazzo, and Pitassi [BIP98]) and $n^{Ω((\log k)/d)}$ (following from a recent formula size lower bound of Rossman [Ros14]). Our lower bound is quite close to optimal, since a simple construction gives depth-$d$ circuits of size $n^{O(k^{2/d})}$ for this problem (and strengthening our bound even to $n^{k^{Ω(1/d)}}$ would require proving that undirected connectivity is not in $\mathsf{NC^1}.$) Our proof is by reduction to a new lower bound on the size of small-depth circuits computing a skewed variant of the "Sipser functions" that have played an important role in classical circuit lower bounds [Sip83, Yao85, Hås86]. A key ingredient in our proof of the required lower bound for these Sipser-like functions is the use of \emph{random projections}, an extension of random restrictions which were recently employed in [RST15]. Random projections allow us to obtain sharper quantitative bounds while employing simpler arguments, both conceptually and technically, than in the previous works [Ajt89, BPU92, BIP98, Ros14].

cs.CC↗

arXiv2015

An inequality for the Fourier spectrum of parity decision trees

We give a new bound on the sum of the linear Fourier coefficients of a Boolean function in terms of its parity decision tree complexity. This result generalizes an inequality of O'Donnell and Servedio for regular decision trees. We use this bound to obtain the first non-trivial lower bound on the parity decision tree complexity of the recursive majority function.

cs.DM↗

arXiv2015

An average-case depth hierarchy theorem for Boolean circuits

We prove an average-case depth hierarchy theorem for Boolean circuits over the standard basis of $\mathsf{AND}$, $\mathsf{OR}$, and $\mathsf{NOT}$ gates. Our hierarchy theorem says that for every $d \geq 2$, there is an explicit $n$-variable Boolean function $f$, computed by a linear-size depth-$d$ formula, which is such that any depth-$(d-1)$ circuit that agrees with $f$ on $(1/2 + o_n(1))$ fraction of all inputs must have size $\exp({n^{Ω(1/d)}}).$ This answers an open question posed by Håstad in his Ph.D. thesis. Our average-case depth hierarchy theorem implies that the polynomial hierarchy is infinite relative to a random oracle with probability 1, confirming a conjecture of Håstad, Cai, and Babai. We also use our result to show that there is no "approximate converse" to the results of Linial, Mansour, Nisan and Boppana on the total influence of small-depth circuits, thus answering a question posed by O'Donnell, Kalai, and Hatami. A key ingredient in our proof is a notion of \emph{random projections} which generalize random restrictions.

cs.CC↗

arXiv2014

New algorithms and lower bounds for monotonicity testing

We consider the problem of testing whether an unknown Boolean function $f$ is monotone versus $ε$-far from every monotone function. The two main results of this paper are a new lower bound and a new algorithm for this well-studied problem. Lower bound: We prove an $\tildeΩ(n^{1/5})$ lower bound on the query complexity of any non-adaptive two-sided error algorithm for testing whether an unknown Boolean function $f$ is monotone versus constant-far from monotone. This gives an exponential improvement on the previous lower bound of $Ω(\log n)$ due to Fischer et al. [FLN+02]. We show that the same lower bound holds for monotonicity testing of Boolean-valued functions over hypergrid domains $\{1,\ldots,m\}^n$ for all $m\ge 2$. Upper bound: We give an $\tilde{O}(n^{5/6})\text{poly}(1/ε)$-query algorithm that tests whether an unknown Boolean function $f$ is monotone versus $ε$-far from monotone. Our algorithm, which is non-adaptive and makes one-sided error, is a modified version of the algorithm of Chakrabarty and Seshadhri [CS13a], which makes $\tilde{O}(n^{7/8})\text{poly}(1/ε)$ queries.

cs.CC↗