Sharp upper bound for quasi polynomial degree of manifold configuration spaces.
problem Determining the exact degree of quasi-polynomial homology groups of configuration spaces.
method Analyzing extremal homology groups of unordered configuration spaces of manifolds.
result The upper bound for the degree of quasi-polynomials is sharp for every manifold.
Algorithm distinguishes Gaussian mixtures from pure Gaussians in quasi-polynomial time.
problem Distinguishing mixtures of Gaussian components from pure Gaussians, especially when components are well-separated.
method Sum-of-Squares method, quasi-polynomial time algorithm, bipartitioning sample to separate components.
result Algorithm can reliably distinguish between mixtures and pure Gaussians in quasi-polynomial time.
Robust learning mixtures of linear regressions improve robustness.
problem Improving robustness in learning mixtures of linear regressions.
method Connecting mixtures of linear regressions and mixtures of Gaussians with thresholding for a quasi-polynomial time algorithm.
result The algorithm has significantly better robustness than previous results.
Efficient algorithm for identifying causal effects in linear models.
problem Determining causal effects from observational data under latent confounding.
method Symbolic computation and efficient algorithm for finding identifying formulas.
result Proves the existence of identifying formulas of a specified degree in quasi-polynomial time.
The paper establishes a nearly-sharp statistical threshold for efficient learning in Latent MDPs with separated components.
problem Learning Latent Markov Decision Processes (LMDPs) with separated components.
method The paper considers various notions of separation and establishes a nearly-sharp statistical threshold for efficient learning. It also presents a quasi-polynomial algorithm with time complexity scaling in terms of the statistical threshold under a weaker assumption of separability under the optimal policy, and a near-matching time complexity lower bound under the exponential time hypothesis.
result Establishes a nearly-sharp statistical threshold for efficient learning in Latent MDPs with separated components.
New algorithm for MDS with quasi-polynomial dependency on aspect ratio.
problem Finding an embedding that minimizes a specific objective function for given dissimilarities.
method A novel geometry-aware analysis of a conditional rounding of the Sherali-Adams LP hierarchy.
result Achieved a solution with cost \(O(\log Δ) \cdot extrm{OPT}^{Ω(1)} + ε\) in quasi-polynomial time.
Algorithm learns halfspaces with Tsybakov noise in polynomial time.
problem PAC learning halfspaces with adversarial noise.
method Reduction to certifying non-optimality, iterative process, warm-start algorithm.
result First polynomial-time algorithm for learning halfspaces with Tsybakov noise.
Let S be an orientable surface with negative Euler characteristic. For k∈N, let Ck(S) denote the k-curve graph, whose vertices are isotopy classes of essential simple closed curves on S, and whose edges correspond to pairs of curves that can be realized to intersect at most …
New algorithm for learning mixtures with mostly uniform weights, improving on previous bounds.
problem Learning mixtures of Gaussians with uniform weights and mostly uniform component weights.
method Statistical Query (SQ) lower bound and quasi-polynomial upper bound for testing.
result Quasi-polynomial upper bound for testing mixtures with mostly uniform weights.
Sparse PCA algorithm improves upon existing methods with better guarantees.
problem Recovering sparse vectors from Gaussian samples with adversarial perturbations.
method New algorithm running in polynomial time with improved β threshold.
result Better guarantees than Covariance Thresholding for large t.
A sequence of rational functions in a variable q is q-holonomic if it satisfies a linear recursion with coefficients polynomials in q and qn. We prove that the degree of a q-holonomic sequence is eventually a quadratic quasi-polynomial. Our proof uses differential Galois theory (adapting proofs regarding hol…
We propose a consistent polynomial-time method for the unseeded node matching problem for networks with smooth underlying structures. Despite widely conjectured by the research community that the structured graph matching problem to be significantly easier than its worst case counterpart, well-known to be NP-hard, the …
In this paper we consider an elementary, and largely unexplored, combinatorial problem in low-dimensional topology. Consider a real 2-dimensional compact surface S, and fix a number of points F on its boundary. We ask: how many configurations of disjoint arcs are there on S whose boundary is F? We find that thi…
We give an algorithm for completing an order-m symmetric low-rank tensor from its multilinear entries in time roughly proportional to the number of tensor entries. We apply our tensor completion algorithm to the problem of learning mixtures of product distributions over the hypercube, obtaining new algorithmic result…
We present a novel parallelisation scheme that simplifies the adaptation of learning algorithms to growing amounts of data as well as growing needs for accurate and confident predictions in critical applications. In contrast to other parallelisation techniques, it can be applied to a broad class of learning algorithms …
Counting essential surfaces in 3-manifolds yields concise formulae and detailed asymptotics.
problem Counting isotopy classes of essential surfaces in 3-manifolds.
method Normal and almost normal surfaces, Ehrhart's lattice point counting, ideal triangulations, and new essential surface testing.
result Quasi-polynomial behavior of surface counts and concise formulae for surface numbers.
Tensor rank and low-rank tensor decompositions have many applications in learning and complexity theory. Most known algorithms use unfoldings of tensors and can only handle rank up to n⌊p/2⌋ for a p-th order tensor in Rnp. Previously no efficient algorithm can decompose 3rd order ten…
We prove the quasimodularity of generating functions for counting pillowcase covers, with and without Siegel-Veech weight. Similar to prior work on torus covers, the proof is based on analyzing decompositions of half-translation surfaces into horizontal cylinders. It provides an alternative proof of the quasimodularity…
We give a simple, fast algorithm for hyperparameter optimization inspired by techniques from the analysis of Boolean functions. We focus on the high-dimensional regime where the canonical example is training a neural network with a large number of hyperparameters. The algorithm --- an iterative application of compresse…
It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient algorithm that achieves an n−1/3-approximation; 2) NP-hardness of approximatio…
Efficient private algorithms for estimating block models and mixture models.
problem Estimating block models and mixture models in high-dimensional settings.
method General tools for designing efficient private estimation algorithms.
result First efficient private algorithms for weak and exact recovery of stochastic block models.
Simplifies and optimizes learning from untrusted batches with structure.
problem Learning from untrusted batches with potential structure.
method Synthesizes techniques from JO19 and CLM19, using Haar wavelets and soft filtering.
result Achieves sublinear sample complexity with polynomial time complexity.
In this article Ehrhart quasi-polynomials of simplices are employed to determine isospectral lens spaces in terms of a finite set of numbers. Using the natural lattice associated with a lens space the associated toric variety of a lens space is introduced. It is proved that if two lens spaces are isospectral then the d…
New algorithm for planning in observable POMDPs in quasi-polynomial time.
problem Planning in POMDPs is computationally hard.
method Assumption of well-separated distributions on states and observations leads to quasi-succinct descriptions of near-optimal policies.
result Quasipolynomial-time algorithm for planning in observable POMDPs.
Based on the presentation of the Kauffman bracket skein module of the torus given by the third author in previous work, Charles D. Frohman and Răzvan Gelca established a complete description of the multiplicative operation leading to a famous product-to-sum formula. In this paper, we study the multiplicative structure …
New algorithm for clustering with faulty oracle achieves optimal queries and efficiency.
problem Clustering with a faulty oracle, especially for multiple clusters.
method Built on stochastic block model, provides nearly-optimal query complexity.
result Time-efficient algorithm with nearly-optimal query complexity for all constant k and any δ.
We prove combinatorially the explicit relation between genus filtrated s-loop means of the Gaussian matrix model and terms of the genus expansion of the Kontsevich--Penner matrix model (KPMM). The latter is the generating function for volumes of discretized (open) moduli spaces Mg,sdisc given by $N_{…
In list-decodable subspace recovery, the input is a collection of n points αn (for some α≪1/2) of which are drawn i.i.d. from a distribution D with a isotropic rank r covariance Π∗ (the \emph{inliers}) and the rest are arbitrary, potential adversarial outliers. The goal is to recover a $O(1/α)…
Cylindrical contact homology linked to Ehrhart polynomials and Chen-Ruan cohomology.
problem Contact invariants of Q-Gorenstein toric contact manifolds.
method Relationships between cylindrical contact homology and Ehrhart polynomials, Chen-Ruan cohomology.
result Cylindrical contact homology invariants linked to Ehrhart polynomials and Chen-Ruan cohomology.
We introduce and study the notion of the G-Tutte polynomial for a list A of elements in a finitely generated abelian group Γ and an abelian group G, which is defined by counting the number of homomorphisms from associated finite abelian groups to G. The G-Tutte polynomial is a common generalizatio…
New lower bound shows RL with linear approximations is computationally hard.
problem Computational hardness in reinforcement learning with linear function approximation.
method Reduction from Unique-Sat to MDPs with linear optimal value functions.
result No randomized polynomial time algorithm exists for RL with linear function approximation unless NP=RP.
Spatial perception is the backbone of many robotics applications, and spans a broad range of research problems, including localization and mapping, point cloud alignment, and relative pose estimation from camera images. Robust spatial perception is jeopardized by the presence of incorrect data association, and in gener…
New method for estimating sparse means in noisy data.
problem Estimating the mean of a sparse distribution in the presence of outliers.
method Difference-of-Pairs Filtering technique for list-decodable sparse mean estimation.
result First sample and computationally efficient algorithm for list-decodable sparse mean estimation.
Algorithm learns mixtures of Gaussians efficiently using diffusion models.
problem Learning mixtures of Gaussians with identity covariance.
method Analytic approach using diffusion models to learn score functions.
result Quasi-polynomial time and sample complexity for learning mixtures.
New algorithms reduce complexity for learning in MDPs with entropy regularization.
problem Efficient learning for MDPs with large or continuous state and action spaces.
method Multilevel Monte Carlo (MLMC) algorithms integrating fixed-point iteration and stochastic approximation of the Bellman operator.
result MLMC with unbiased approximation of the Bellman operator achieves polynomial sample complexity.
New algorithm learns sparse linear MDPs with polynomial interactions, improving sample complexity.
problem Learning optimal policies in sparse linear MDPs with limited interactions and unknown features.
method Developed a polynomial-time algorithm using feature selection and emulator for sparse linear MDPs.
result First polynomial-time algorithm for learning near-optimal policies in k-sparse linear MDPs.
New method certifies anti-concentration for various non-Gaussian distributions.
problem Efficiently certifying anti-concentration for non-Gaussian distributions.
method Sum-of-Squares relaxation of integer program for anti-concentration.
result Quasi-polynomial time certificates for non-Gaussian distributions.
A new algorithm reduces sampling complexity for general distributions.
problem Sampling from complex target distributions efficiently.
method Recursive score estimation method for diffusion-based Monte Carlo.
result Gradient complexity improved from exponential to quasi-polynomial.
Algorithm learns halfspaces in noisy data efficiently.
problem Learning halfspaces with Tsybakov noise.
method Novel semi-definite programming and online convex optimization.
result First non-trivial PAC learning algorithm for Tsybakov noise.
New algorithm recovers 3D molecule structures from noisy data.
problem Recovering 3D molecule structures from noisy, randomly rotated copies.
method Smoothed analysis of orbit recovery over SO(3) using frequency marching. result Quasi-polynomial time algorithm for orbit recovery over SO(3). Study on recovering supports of multiple sparse vectors from mixed linear measurements.
problem Recovering supports of multiple sparse vectors from a mixture of linear measurements.
method Developed algorithms to identify the support of all component vectors using polynomial and quasi-polynomial number of measurements.
result Polynomial and quasi-polynomial number of measurements sufficient for recovering the supports of all component vectors.
Paper bridges score estimation to parameter and density estimation in DDPMs.
problem Efficiently estimating scores for generative models.
method Introduces a framework linking score estimation to parameter and density estimation.
result Denoising score-matching in DDPMs is asymptotically efficient for parameter estimation.
The paper explores privacy-preserving methods for counting unique elements in distributed settings.
problem Counting unique elements in a distributed setting while maintaining privacy.
method Analyzes and proves lower bounds for differentially private protocols in various settings.
result Achieves optimal error bounds for multi-message shuffle protocols in estimating distinct elements.
In this paper, we study the problem of estimating smooth Generalized Linear Models (GLMs) in the Non-interactive Local Differential Privacy (NLDP) model. Different from its classical setting, our model allows the server to access some additional public but unlabeled data. In the first part of the paper we focus on GLMs…
New sampling algorithm for non-log-concave distributions requires many queries.
problem Sampling from non-log-concave distributions with good accuracy.
method Lower bound on query complexity and algorithm for sampling.
result Tight query complexity characterization for sampling from non-log-concave distributions.
Improved sampling from non-log-concave distributions with polynomial query complexity.
problem Sampling from distributions with non-log-concave densities efficiently.
method Combining Ornstein-Uhlenbeck process assumptions and polynomial moment conditions.
result Polynomial query complexity improvement over previous methods.
Analyzes intrinsic time in financial markets, linking it to physical time.
problem Understanding the intrinsic nature of time in financial data.
method Presented an analytic relationship linking intrinsic and physical time, using empirical scaling laws.
result A novel empirical scaling law relating intrinsic time variability to overshoots.
Consider power utility maximization of terminal wealth in a 1-dimensional continuous-time exponential Levy model with finite time horizon. We discretize the model by restricting portfolio adjustments to an equidistant discrete time grid. Under minimal assumptions we prove convergence of the optimal discrete-time strate…