Noise Sensitivity Exponent controls statistical-computational gaps in learning.
problem Understanding when learning is statistically possible yet computationally hard in high-dimensional statistics.
method Investigating statistical-computational gaps in single- and multi-index models using Noise Sensitivity Exponent.
result Noise Sensitivity Exponent governs statistical-computational gaps in high-dimensional learning.
New computational lower bounds for clustering and related problems.
problem Statistical-computational gaps in high-dimensional clustering problems.
method Investigation of low-degree polynomials in latent space models to derive lower bounds.
result New and sharper computational lower bounds for clustering, sparse clustering, and biclustering.
Statistical-computational gap found in aligning multiple Gaussian graphs.
problem Aligning multiple Gaussian graphs with unknown signals.
method Generalized informational threshold and computational barrier analysis.
result Existence of a statistical-computational gap in multiple Gaussian graph alignment.
In these notes we describe heuristics to predict computational-to-statistical gaps in certain statistical problems. These are regimes in which the underlying statistical problem is information-theoretically possible although no efficient algorithm exists, rendering the problem essentially unsolvable for large instances…
Polynomial-time algorithm finds planted hypercube vectors in Gaussian mixtures.
problem Clustering d-dimensional Gaussian mixtures with unknown covariance.
method Lattice-based methods using Lenstra--Lenstra--Lovasz reduction.
result Achieves statistically-optimal sample complexity of d+1 samples.
Study shows computational and statistical gaps in Gaussian Single-Index Models.
problem Statistical and computational trade-offs in high-dimensional regression problems.
method Analysis of SQ and LDP frameworks, partial-trace algorithm.
result Computational algorithms require significantly more samples than information-theoretic limits.
Efficient method for tensor linear form inference with noisy incomplete data.
problem Statistical inference of tensor linear forms with incomplete and noisy observations.
method Initial estimate + debiasing + one-step power iteration.
result Optimal uncertainty quantification and statistical-to-computational gaps examined.
We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability 1−α. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the statistical accuracies and computational efficiency of these algorithms depend on the degr…
New method explains computational barriers in high-dimensional statistical models.
problem Understanding detection-recovery gaps in high-dimensional inference.
method Combining algorithmic contiguity and cross-validation reduction to obtain conditional computational lower bounds.
result Mild control of low-degree advantage is sufficient to explain computational barriers for recovery.
New insights link diverse statistical problems via secret leakage planted clique.
problem Statistical-computational gaps in inference problems.
method Secret leakage planted clique as a new hardness assumption for reductions.
result Establishes tight statistical-computational tradeoffs for various problems.
Privacy improves robustness in statistical estimation.
problem Sparse mean estimation under privacy constraints.
method Sum-of-Squares method and exponential-time mechanisms.
result Private algorithms matching optimal tradeoffs are not known, but achieved via Sum-of-Squares.
Lasso performs poorly with correlated covariates, but a rescaled approach fixes this.
problem Lasso's performance degrades with correlated covariates, leading to inefficiency.
method Proposes a rescaling method for Lasso to handle correlated covariates effectively.
result Rescaled Lasso provides strong provable guarantees for estimation with quadratic sample complexity.
New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.
problem Connecting tensor responses to tensor covariates with unknown intrinsic rank.
method Riemannian gradient descent and Riemannian Gauss-Newton methods for tensor-on-tensor regression.
result Riemannian optimization methods converge linearly and quadratically to a statistically optimal estimate in rank over-parameterized settings.
Characterizes optimal reconstruction error in high-dimensional Gaussian mixtures.
problem Optimizing reconstruction error in high-dimensional sparse Gaussian mixtures.
method Exact asymptotic characterization using state evolution of AMP algorithm.
result Identification of statistical-to-computational gap between AMP and information-theoretic threshold.
Study potential computational gaps in symmetric binary perceptrons using fl-RDT.
problem Potential statistical-computational gaps in symmetric binary perceptrons.
method Parametric utilization of fully lifted random duality theory (fl-RDT).
result Observation of a computational gap SCG=αc−αa in SBP. Develops methods to estimate high rank tensors from noisy data.
problem Estimating high rank tensors from noisy observations.
method Generative latent variable tensor model, polynomial-time spectral algorithm.
result Achieves computationally optimal rate for signal tensor estimation.
We study the fundamental tradeoffs between statistical accuracy and computational tractability in the analysis of high dimensional heterogeneous data. As examples, we study sparse Gaussian mixture model, mixture of sparse linear regressions, and sparse phase retrieval model. For these models, we exploit an oracle-based…
Paper studies statistical-computational trade-offs in tensor PCA and related problems.
problem Statistical-computational gap in tensor PCA estimation.
method Derives computational lower bounds using communication complexity.
result Lower bounds specify trade-off among passes, sample size, and memory.
Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this contribution, we provide a rigorous justification of these approaches for a two-layers ne…
Study on detecting and recovering hidden dense cycles in random graphs.
problem Detecting and recovering hidden dense cycles in random graphs.
method Information-theoretic analysis of thresholds for detection and recovery.
result Characterization of information-theoretic thresholds for detection and recovery.
This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and a universality principle for these gaps. A main feature of our approach is to ma…
New method uses almost orthonormal bases to prove low-degree lower bounds in complex statistical models.
problem Proving statistical-computational gaps in high-dimensional models with planted structures.
method Constructing an almost orthonormal polynomial basis under the planted distribution.
result Established new low-degree lower bounds for various complex models.
New study shows limits of low-degree algorithms in finding large independent sets in sparse hypergraphs.
problem Finding large independent sets in sparse random hypergraphs.
method Low-degree polynomial algorithms are analyzed to determine their limits.
result Low-degree algorithms can find independent sets of density up to \(\left(\frac{\log d}{(r-1)d}
ight)^{1/(r-1)}\), but no larger.
Price gap, defined as the logarithmic price difference between the first two occupied price levels on the same side of a limit order book (LOB), is a key determinant of market depth, which is one of the dimensions of liquidity. However, the properties of price gaps have not been thoroughly studied due to the less avail…
Statistical mechanics explains learning in large neural networks near interpolation.
problem Understanding the learning dynamics of large neural networks near interpolation.
method Statistical physics analysis of a two-layer network with generic weight distribution and activation function.
result Learning transitions and feature learning emerge as the number of data increases.
This paper simplifies computing higher-order U-statistics efficiently.
problem The inefficiency of computing higher-order U-statistics in practice. method Decomposition, connection to Einstein summation, and treewidth-based complexity estimate.
result A new, more efficient algorithm to compute U-statistics. Statistical query algorithms and low-degree tests are nearly equivalent in high-dimensional hypothesis testing.
problem High-dimensional hypothesis testing and information-computation gaps.
method Analysis of statistical query framework and low-degree polynomials.
result Statistical query algorithms and low-degree polynomials are almost equivalent in power under mild conditions.
Deep learning uncovers patterns between knot types.
problem Discovering connections between combinatorial and hyperbolic knot invariants.
method Statistical approach using linear regression and deep learning.
result Revealed empirical connections between knot types.
Study optimal algorithms for recovering signals through inhomogeneous low-rank channels.
problem Recovering signals through an inhomogeneous low-rank matrix channel.
method Derive and analyze an approximate message-passing algorithm (AMP) and a spectral method.
result The AMP iteration matches the conjectured optimal computational phase transition.
We study the fundamental tradeoffs between computational tractability and statistical accuracy for a general family of hypothesis testing problems with combinatorial structures. Based upon an oracle model of computation, which captures the interactions between algorithms and data, we establish a general lower bound tha…
Estimation under missing data shows computational and statistical limits for Gaussian data.
problem Estimation of population parameters in high-dimensional data with missing data.
method Analysis of computational and statistical limits for mean and covariance estimation, and linear regression.
result Statistical-computational gaps exist for mean and covariance estimation, but not for linear regression.
Study phase transitions in identifying infected individuals using group testing.
problem Identifying a set of k infected individuals from a population using pooled tests.
method Two random assignment designs (constant-column and Bernoulli) and polynomial-time inference procedures.
result Sharp phase transitions in statistical and computational limits for detection and recovery problems.
The paper introduces gapped scale-sensitive dimensions to improve learning rate bounds.
problem Improving lower bounds on rates of convergence in statistical and online learning.
method Introducing and analyzing gapped scale-sensitive dimensions for function classes.
result Gapped dimensions lead to stronger lower bounds on offset Rademacher averages.
New research shows some distributions hard to sample via diffusions.
problem Some distributions hard to sample via diffusions.
method Learning drifts of diffusions to approximate target distributions.
result Superpolynomially close drifts can yield very far approximations.
Study on multi-agent decision making complexity, showing sample efficiency gaps.
problem Understanding sample efficiency in multi-agent decision making.
method General framework for interactive decision making, focusing on equilibrium computation.
result No 'reasonable' complexity measure can close gaps between single and multiple agents.
Paper addresses eigenvector perturbation in small eigen-gap scenarios.
problem Fine-grained behavior of eigenvectors in the presence of small eigen-gaps.
method Develops de-biased estimators for linear functions of an unknown eigenvector.
result Achieves minimax lower bounds for a family of scenarios, even with small eigen-gaps.
Improved robust regression with clean covariates achieves better rates than Huber's model.
problem Robust regression under adaptive contamination of responses with clean covariates.
method Exploiting clean covariates to construct an estimator achieving better rates than Huber's model.
result Improved estimation rate even with constant contamination, achieving consistency.
Study optimizes compute usage for LLM web agents, improving performance.
problem High compute costs and narrow focus on single-step tasks limit LLM web agents.
method Two-stage pipeline: SFT followed by on-policy RL, with hyperparameter optimization.
result Combining SFT and on-policy RL requires 55% less compute to match peak SFT performance.
We investigate the statistics of the gap, G_n, between the two rightmost positions of a Markovian one-dimensional random walker (RW) after n time steps and of the duration, L_n, which separates the occurrence of these two extremal positions. The distribution of the jumps η_i's of the RW, f(η), is symmetric and its Four…
SGD learns sparse parities near computational limits with discontinuous phase transitions.
problem Learning sparse parities in deep learning.
method Empirical and theoretical analysis of SGD on sparse parities.
result SGD makes progress on sparse parities via Fourier gap, not Langevin-like mechanism.
New insights into statistical and computational limits for mixed sparse linear regression.
problem Recovering two sparse signals from noisy linear measurements.
method Analysis of low-degree polynomials and a simple thresholding algorithm.
result Identification of a smooth information-computation tradeoff and order-optimality of the thresholding algorithm.
The interplay between computational efficiency and statistical accuracy in high-dimensional inference has drawn increasing attention in the literature. In this paper, we study computational and statistical boundaries for submatrix localization. Given one observation of (one or multiple non-overlapping) signal submatrix…
New methods reduce bias in estimating optimality gaps for risk-averse stochastic programs.
problem Optimality gap estimation bias in risk-averse stochastic programs.
method Two independent samples, each estimating a different component of the optimality gap.
result Our method reduces bias in estimating optimality gaps for risk-averse problems.
Study shows generative priors improve rank-one matrix recovery with optimal sample complexity.
problem Recovering a rank-one signal matrix from noisy data with additional prior information.
method Analysis of a nonlinear least squares objective with a favorable global optimization landscape.
result Established optimal sample complexity for generative priors in rank-one matrix recovery.
ST-BCP narrows the coverage gap in BCP by transforming nonconformity scores.
problem The looseness in BCP's coverage guarantee due to Markov's inequality.
method Introduces a data-dependent transformation of nonconformity scores.
result Reduces the average coverage gap from 4.20% to 1.12% on benchmarks.
This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.
problem Characterizing statistical computational gaps in symmetric binary perceptrons.
method Developed an analytical union-bounding program to rigorously upper-bound constraint densities of ultrametric overlap gap properties.
result Obtained tightest bounds at the first two levels of ultrametric overlap gap properties, closely approaching parametric RDT estimates.
Paper proposes efficient methods for high-order clustering in tensor block models.
problem High-order clustering of multiway datasets in neuroimaging, genomics, etc.
method Tensor block model and computationally efficient algorithms (HLloyd, HSC)
result Achieves high-order exact clustering with statistical optimality and computational efficiency.
Database theory and database practice are typically the domain of computer scientists who adopt what may be termed an algorithmic perspective on their data. This perspective is very different than the more statistical perspective adopted by statisticians, scientific computers, machine learners, and other who work on wh…