Searcharxiv⌕ Search

arXiv subjects

Karthik Gajulapalli

Publications and source records attributed to Karthik Gajulapalli.

8 recordsLinked to original sources
arXiv2026

Online Orthogonal Vectors Revisited

We prove new upper and lower bounds for the Online Orthogonal Vectors Problem ($\mathsf{OnlineOV}_{n,d}$). In this problem, a preprocessing algorithm receives $n$ vectors $x_1,\ldots,x_n\in\{0,1\}^d$ and constructs a data structure of size $S$. A query algorithm subsequently receives a query vector $q\in\{0,1\}^d$ and in time $T$ decides whether $q$ is orthogonal to any of the input vectors $x_i$. We design a new deterministic data structure for $\mathsf{OnlineOV}_{n,d}$. In low dimensions ($d = c \log n$), our data structure matches the performance of the best known randomized algorithm due to Chan [SoCG 2017]. Furthermore, in moderate dimensions ($d=n^{\varepsilon}$), we give the first improvement since Charikar, Indyk and Panigrahy [ICALP 2002]. Along the way, we give the first deterministic refutation of a conjecture on the hardness of $\mathsf{OnlineOV}$ posed by Goldstein, Lewenstein and Porat [ISAAC 2017]. This data structure also extends to a number of problems, including Partial Match, Orthogonal Range Search, and DNF Evaluation. We use a novel structure-versus-randomness decomposition to design our algorithm. Under the Non-Uniform Strong Exponential Time Hypothesis, we also prove arbitrarily large polynomial space lower bounds for any $\mathsf{OnlineOV}$ data structure with sublinear query time even with computationally unbounded preprocessing. These lower bounds extend to several other problems, including Polynomial Evaluation, Partial Match, Orthogonal Range Search, and Approximate Nearest Neighbors. We also prove similar lower bounds for $\mathsf{3-SUM}$ with preprocessing under the Non-Uniform Hamiltonian Path Conjecture.

cs.DS↗
arXiv2025

Oblivious Complexity Classes Revisited: Lower Bounds and Hierarchies

In this work we study oblivious complexity classes. These classes capture the power of interactive proofs where the prover(s) are only given the input size rather than the actual input. In particular, we study the connections between the symmetric polynomial time $\mathsf{S_2P}$ and its oblivious counterpart $\mathsf{O_2P}$. Among our results, we construct an explicit language in $\mathsf{O_2P}$ that cannot be computed by circuits of size $n^k$, and thus prove a hierarchy theorem for $\mathsf{O_2TIME}$. Along the way we also make partial progress towards the resolution of an open question posed by Goldreich and Meir (TOCT 2015) that relates the complexity of $\mathsf{NP}$ to its oblivious counterpart $\mathsf{ONP}$. To the best of our knowledge, these results constitute the first explicit fixed-polynomial lower bound and hierarchy theorem for $\mathsf{O_2P}$. The smallest uniform complexity class for which such lower bounds were previously known was $\mathsf{S_2P}$, due to Cai (JCSS 2007). In addition, this is the first uniform hierarchy theorem for a semantic class. All previous results required some non-uniformity.

cs.CC↗
arXiv2025

Output-Sparse Matrix Multiplication Using Compressed Sensing

We give two algorithms for output-sparse matrix multiplication (OSMM), the problem of multiplying two $n \times n$ matrices $A, B$ when their product $AB$ is promised to have at most $O(n^δ)$ many non-zero entries for a given value $δ\in [0, 2]$. We then show how to speed up these algorithms in the fully sparse setting, where the input matrices $A, B$ are themselves sparse. All of our algorithms work over arbitrary rings. Our first, deterministic algorithm for OSMM works via a two-pass reduction to compressed sensing. It runs in roughly $n^{ω(δ/2, 1, 1)}$ time, where $ω(\cdot, \cdot, \cdot)$ is the rectangular matrix multiplication exponent. This substantially improves on prior deterministic algorithms for output-sparse matrix multiplication. Our second, randomized algorithm for OSMM works via a reduction to compressed sensing and a variant of matrix multiplication verification, and runs in roughly $n^{ω(δ- 1, 1, 1)}$ time. This algorithm and its extension to the fully sparse setting have running times that match those of the (randomized) algorithms for OSMM and FSMM, respectively, in recent work of Abboud, Bringmann, Fischer, and Künnemann (SODA, 2024). Our algorithm uses different techniques and is arguably simpler. Finally, we observe that the running time of our randomized algorithm and the algorithm of Abboud et al. are optimal via a simple reduction from rectangular matrix multiplication.

cs.DS↗
arXiv2025

Downward self-reducibility in the total function polynomial hierarchy

A problem $\mathcal{P}$ is considered downward self-reducible, if there exists an efficient algorithm for $\mathcal{P}$ that is allowed to make queries to only strictly smaller instances of $\mathcal{P}$. Downward self-reducibility has been well studied in the case of decision problems, and it is well known that any downward self-reducible problem must lie in $\mathsf{PSPACE}$. Harsha, Mitropolsky and Rosen [ITCS, 2023] initiated the study of downward self reductions in the case of search problems. They showed the following interesting collapse: if a problem is in $\mathsf{TFNP}$ and also downward self-reducible, then it must be in $\mathsf{PLS}$. Moreover, if the problem admits a unique solution then it must be in $\mathsf{UEOPL}$. We demonstrate that this represents just the tip of a much more general phenomenon, which holds for even harder search problems that lie higher up in the total function polynomial hierarchy ($\mathsf{TFΣ_i^P}$). In fact, even if we allow our downward self-reduction to be much more powerful, such a collapse will still occur. We show that any problem in $\mathsf{TFΣ_i^P}$ which admits a randomized downward self-reduction with access to a $\mathsf{Σ_{i-1}^P}$ oracle must be in $\mathsf{PLS}^{\mathsf{Σ_{i-1}^P}}$. If the problem has \textit{essentially unique solutions} then it lies in $\mathsf{UEOPL}^{\mathsf{Σ_{i-1}^P}}$. As one (out of many) application of our framework, we get new upper bounds for the problems $\mathrm{Range Avoidance}$ and $\mathrm{Linear Ordering Principle}$ and show that they are both in $\mathsf{UEOPL}^{\mathsf{NP}}$.

cs.CC↗
arXiv2024

Matrix Multiplication Verification Using Coding Theory

We study the Matrix Multiplication Verification Problem (MMV) where the goal is, given three $n \times n$ matrices $A$, $B$, and $C$ as input, to decide whether $AB = C$. A classic randomized algorithm by Freivalds (MFCS, 1979) solves MMV in $\widetilde{O}(n^2)$ time, and a longstanding challenge is to (partially) derandomize it while still running in faster than matrix multiplication time (i.e., in $o(n^ω)$ time). To that end, we give two algorithms for MMV in the case where $AB - C$ is sparse. Specifically, when $AB - C$ has at most $O(n^δ)$ non-zero entries for a constant $0 \leq δ< 2$, we give (1) a deterministic $O(n^{ω- \varepsilon})$-time algorithm for constant $\varepsilon = \varepsilon(δ) > 0$, and (2) a randomized $\widetilde{O}(n^2)$-time algorithm using $δ/2 \cdot \log_2 n + O(1)$ random bits. The former algorithm is faster than the deterministic algorithm of Künnemann (ESA, 2018) when $δ\geq 1.056$, and the latter algorithm uses fewer random bits than the algorithm of Kimbrel and Sinha (IPL, 1993), which runs in the same time and uses $\log_2 n + O(1)$ random bits (in turn fewer than Freivalds's algorithm). We additionally study the complexity of MMV. We first show that all algorithms in a natural class of deterministic linear algebraic algorithms for MMV (including ours) require $Ω(n^ω)$ time. We also show a barrier to proving a super-quadratic running time lower bound for matrix multiplication (and hence MMV) under the Strong Exponential Time Hypothesis (SETH). Finally, we study relationships between natural variants and special cases of MMV (with respect to deterministic $\widetilde{O}(n^2)$-time reductions).

cs.DS↗
arXiv2023

Range Avoidance for Constant-Depth Circuits: Hardness and Algorithms

Range Avoidance (AVOID) is a total search problem where, given a Boolean circuit $C\colon\{0,1\}^n\to\{0,1\}^m$, $m>n$, the task is to find a $y\in\{0,1\}^m$ outside the range of $C$. For an integer $k\geq 2$, $\mathrm{NC}^0_k$-AVOID is a special case of AVOID where each output bit of $C$ depends on at most $k$ input bits. While there is a very natural randomized algorithm for AVOID, a deterministic algorithm for the problem would have many interesting consequences. Ren, Santhanam, and Wang (FOCS 2022) and Guruswami, Lyu, and Wang (RANDOM 2022) proved that explicit constructions of functions of high formula complexity, rigid matrices, and optimal linear codes, reduce to $\mathrm{NC}^0_4$-AVOID, thus establishing conditional hardness of the $\mathrm{NC}^0_4$-AVOID problem. On the other hand, $\mathrm{NC}^0_2$-AVOID admits polynomial-time algorithms, leaving the question about the complexity of $\mathrm{NC}^0_3$-AVOID open. We give the first reduction of an explicit construction question to $\mathrm{NC}^0_3$-AVOID. Specifically, we prove that a polynomial-time algorithm (with an $\mathrm{NP}$ oracle) for $\mathrm{NC}^0_3$-AVOID for the case of $m=n+n^{2/3}$ would imply an explicit construction of a rigid matrix, and, thus, a super-linear lower bound on the size of log-depth circuits. We also give deterministic polynomial-time algorithms for all $\mathrm{NC}^0_k$-AVOID problems for $m\geq n^{k-1}/\log(n)$. Prior work required an $\mathrm{NP}$ oracle, and required larger stretch, $m \geq n^{k-1}$.

cs.CC↗
arXiv2020

Stability-Preserving, Time-Efficient Mechanisms for School Choice in Two Rounds

We address the following dynamic version of the school choice question: a city, named City, admits students in two temporally-separated rounds, denoted $\mathcal{R}_1$ and $\mathcal{R}_2$. In round $\mathcal{R}_1$, the capacity of each school is fixed and mechanism $\mathcal{M}_1$ finds a student optimal stable matching. In round $\mathcal{R}_2$, certain parameters change, e.g., new students move into the City or the City is happy to allocate extra seats to specific schools. We study a number of Settings of this kind and give polynomial time algorithms for obtaining a stable matching for the new situations. It is well established that switching the school of a student midway, unsynchronized with her classmates, can cause traumatic effects. This fact guides us to two types of results, the first simply disallows any re-allocations in round $\mathcal{R}_2$, and the second asks for a stable matching that minimizes the number of re-allocations. For the latter, we prove that the stable matchings which minimize the number of re-allocations form a sublattice of the lattice of stable matchings. Observations about incentive compatibility are woven into these results. We also give a third type of results, namely proofs of NP-hardness for a mechanism for round $\mathcal{R}_2$ under certain settings.

cs.GT↗