New bounds show complex neural networks need many queries to learn.
problem Learning non-polynomial activation functions with Gaussian marginals.
method Gradient boosting procedure to amplify lower bounds on SQ dimension of neural networks.
result Statistical-query lower bounds for ReLU regression with 2 n c ε 2^{n^c} ε 2 n c ε queries. Statistical Query lower bound shows difficulty in list-decodable linear regression.
problem List-decodable linear regression with adversarial corruption.
method Statistical Query (SQ) lower bound analysis.
result Lower bound of d p o l y ( 1 / α ) d^{\mathrm{poly}(1/α)} d poly ( 1/ α ) for list-decodable linear regression. 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.
Lower bounds show density estimation requires linear samples or query time.
problem Statistical-computational trade-offs in density estimation.
method Lower bound analysis on data structures.
result Lower bounds demonstrate statistical-computational trade-offs for density estimation.
Proves SQ lower bounds for learning two-hidden-layer neural networks.
problem Learning two-hidden-layer ReLU networks with Gaussian inputs.
method Refined lifting procedure to reduce Boolean PAC learning to Gaussian.
result Superpolynomial SQ lower bounds for Gaussian inputs.
Lower bound shows super-polynomial gap for estimating truncated Gaussian means.
problem Estimating mean of truncated Gaussian distribution with limited samples.
method Statistical Query (SQ) lower bounds for learning.
result Super-polynomial information-computation gap for the task.
Paper solves k-sparse parity problem with sign SGD, matching SQ lower bound.
problem Solving k-sparse parity problems efficiently.
method Sign stochastic gradient descent on neural networks.
result Matches Statistical Query lower bound for solving k-sparse parity problems.
Gradient descent fails to learn simple neural networks efficiently.
problem Learning one-layer neural networks efficiently using gradient descent.
method Gradient descent and statistical query algorithms.
result Superpolynomial lower bounds for learning one-layer neural networks.
The study sets limits on how well halfspaces can be learned when labels are corrupted.
problem Learning halfspaces in the presence of Massart noise.
method Statistical query (SQ) lower bounds.
result No SQ algorithm can achieve misclassification error better than the corruption rate η η η with superpolynomial accuracy or a superpolynomial number of queries. Study private query release with public data, reducing sample sizes.
problem Answering a wide range of statistical queries while maintaining privacy.
method Combines public and private samples to answer queries with differential privacy.
result Private and public sample complexities for different query classes.
Optimized Franz-Parisi criterion matches SQ lower bounds for various statistical models.
problem Understanding computational hardness in statistical inference.
method Proposed and refined Franz-Parisi criterion, established equivalence with SQ lower bounds.
result Optimized Franz-Parisi criterion is equivalent to Statistical Query (SQ) lower bounds.
New SQ lower bounds show learning mixtures of bounded covariance Gaussians is hard.
problem Learning mixtures of Gaussians with bounded covariance matrices is hard.
method Statistical Query (SQ) lower bounds.
result Any SQ algorithm requires complexity at least d Ω ( 1 / ε ) d^{Ω(1/ε)} d Ω ( 1/ ε ) for learning mixtures of bounded covariance Gaussians. Tensor PCA problem analyzed with statistical query lower bounds.
problem Estimating the expected value of a rank-1 tensor from Gaussian samples.
method Sharp analysis of optimal sample complexity in the Statistical Query model.
result SQ algorithms with polynomial query complexity fail in the conjectured hard phase and have sub-optimal sample complexity.
New SQ lower bound shows complexity nearly matches known upper bound for smoothed agnostic learning.
problem Smoothed agnostic learning of halfspaces under subgaussian distributions.
method Statistical Query (SQ) lower bound using moment-matching hard distribution and linear programming duality.
result First non-trivial lower bound on complexity nearly matches known upper bound.
Optimal SQ bounds for learning binary product distributions and Ising models.
problem Learning binary product distributions and Ising models robustly.
method Statistical Query (SQ) lower bounds for robust learning.
result Optimal SQ lower bounds match known algorithm error guarantees.
Study near-optimal bounds for learning Gaussian halfspaces with random noise.
problem Learning general halfspaces with Gaussian distribution and random classification noise.
method Established nearly-matching algorithmic and SQ lower bounds, developed a computationally efficient learning algorithm.
result Sample complexity of learning algorithm is O ( d / ε + d / ( max { p , ε } ) 2 ) O(d/ε + d/(\max\{p, ε\})^2) O ( d / ε + d / ( max { p , ε } ) 2 ) , SQ lower bound is Ω ( d 1 / 2 / ( max { p , ε } ) 2 ) Ω(d^{1/2}/(\max\{p, ε\})^2) Ω ( d 1/2 / ( max { p , ε } ) 2 ) . Paper develops PAC verification for hypothesis classes and statistical algorithms.
problem Verifying machine learning models interactively.
method Develops interactive proof for PAC verification, proves lower bounds, and introduces a generalization.
result Improved protocol for verifying unions of intervals and statistical query algorithms.
The study establishes SQ lower bounds for learning halfspaces and ReLUs under Gaussian marginals.
problem Agnostically learning halfspaces and ReLUs under Gaussian marginals.
method Statistical Query (SQ) lower bounds analysis.
result Proves SQ lower bounds of d p o l y ( 1 / ε ) d^{\mathrm{poly}(1/ε)} d poly ( 1/ ε ) for both problems. This work sets lower bounds on the number of score queries needed for diffusion sampling.
problem Establishing information-theoretic limits on the number of score evaluations required for diffusion sampling.
method Proving lower bounds on the number of adaptive score queries needed for sampling.
result Any sampling algorithm requires at least \(\widetilde{\Omega}(\sqrt{d})\) adaptive score queries for \(d\)-dimensional distributions.
Improved efficient robust regression with near-linear time and subquadratic samples.
problem Robust linear regression with unknown covariance matrix under Gaussian covariates.
method Near-linear time algorithm using subquadratic samples, complemented by SQ and polynomial lower bounds.
result Achieves prediction error O ( ε κ ) O(\sqrt{εκ}) O ( ε κ ) for ε κ ≲ 1 εκ\lesssim 1 ε κ ≲ 1 , improving over prior works. New SQ lower bounds for NGCA without requiring chi-squared condition.
problem Proving SQ hardness for NGCA under moment-matching conditions.
method General SQ lower bound methodology applied to NGCA under moment-matching conditions.
result Proved near-optimal SQ lower bounds for NGCA without chi-squared condition.
New algorithm for learning ReLU networks with Gaussian noise, improving previous results.
problem PAC learning one-hidden-layer ReLU networks with Gaussian marginals and label noise.
method First polynomial-time algorithm for k k k up to i l d e O ( log d ) ilde{O}(\sqrt{\log d}) i l d e O ( log d ) for positive coefficients, no assumptions on rank or condition number. result Proves a Statistical Query lower bound of d Ω ( k ) d^{Ω(k)} d Ω ( k ) for arbitrary real coefficients, separating learnability classes. New lower bounds for sampling from log-concave distributions in higher dimensions.
problem Proving lower bounds for sampling from log-concave distributions in higher dimensions.
method Multiscale construction inspired by geometric measure theory and reduction to block Krylov algorithms.
result Query lower bounds for sampling from log-concave distributions in higher dimensions are established.
Lower bounds show learning mixtures of linear classifiers is nearly impossible.
problem Learning mixtures of linear classifiers under Gaussian covariates.
method Statistical Query (SQ) lower bounds and new spherical designs.
result Complexity of any SQ algorithm is \( n^{\mathrm{poly}(1/Δ) \log(r)} \), where Δ is the pairwise \(\ell_2\)-separation.
Sum-of-Squares lower bound shows NGCA requires more samples than known algorithms.
problem Finding a non-Gaussian direction in a high-dimensional dataset.
method Sum-of-Squares (SoS) framework to prove lower bounds.
result First super-constant degree SoS lower bound for NGCA.
A new method for private query release using Johnson-Lindenstrauss projection.
problem Private release of query answers with minimal privacy loss.
method Random projection of query answers to a lower dimension, followed by noise addition.
result Optimal worst-case sample complexity for answering a workload of k queries.
New lower bounds show learning intersections of halfspaces is hard even for a few halfspaces.
problem Learning intersections of halfspaces in polynomial time under standard assumptions.
method Unified connection to parallel pancakes distribution for proving hardness.
result Learning ω ( log log N ) ω(\log \log N) ω ( log log N ) halfspaces in dimension N N N requires super-polynomial time under standard assumptions. We consider the problem of sampling from a strongly log-concave density in R d \mathbb{R}^d R d , and prove an information theoretic lower bound on the number of stochastic gradient queries of the log density needed. Several popular sampling algorithms (including many Markov chain Monte Carlo methods) operate by using stochas…
New method generates private synthetic data with optimal utility for smooth queries.
problem Achieving strong utility guarantees for meaningful downstream analysis of sensitive datasets.
method Proposes a polynomial-time algorithm for generating ( ε , δ ) (\varepsilon,δ) ( ε , δ ) -differentially private synthetic data with minimax optimal error rates for smooth queries. result Achieves a minimax error rate of O k , d ( n − min { 1 , k d } ) O_{k,d}(n^{-\min \{1, \frac{k}{d}\}}) O k , d ( n − m i n { 1 , d k } ) for k k k -smooth queries, up to a log ( n ) \log(n) log ( n ) factor. Study shows SQ lower bounds for learning ReLUs with Massart noise.
problem Learning a single neuron in the presence of Massart noise.
method Statistical Query (SQ) lower bounds for efficient learning algorithms.
result No efficient SQ algorithm can approximate the optimal error within any constant factor.
Near-optimal SQ hardness shows learning halfspaces with Massart noise is hard.
problem Learning halfspaces with Massart noise in the presence of label corruption.
method Statistical Query (SQ) model analysis.
result No efficient SQ algorithm can achieve better than Ω ( η ) Ω(η) Ω ( η ) error, even for optimal noise levels. New algorithm for reliable learning of Gaussian halfspaces with improved sample and computational complexity.
problem Learning halfspaces under Gaussian marginals with reliable agnostic model.
method Developed a new algorithm for reliable learning of Gaussian halfspaces with specific sample and computational complexity.
result Achieved a new algorithm with improved sample and computational complexity for reliable learning of Gaussian halfspaces.
New insights into query complexity for Nash equilibrium learning.
problem Characterizing the number of queries needed to learn approximate Nash equilibria in matrix games.
method Introduced a new technique to prove lower bounds on query complexity, improving previous techniques.
result Lower bounds of order Ω ( log ( 1 K ε ) ) Ω(\log(\frac{1}{Kε})) Ω ( log ( K ε 1 )) for any ε ≤ 1 / ( c K 4 ) ε\leq 1 / (cK^4) ε ≤ 1/ ( c K 4 ) , where c c c is a constant. We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly nat…
Study shows SQ hardness for multiclass linear classification with random noise.
problem Complexity of multiclass linear classification with random noise.
method Proves super-polynomial SQ lower bounds for MLC with RCN.
result Super-polynomial SQ lower bounds for MLC with RCN.
We lower bound the complexity of finding ε ε ε -stationary points (with gradient norm at most ε ε ε ) using stochastic first-order methods. In a well-studied model where algorithms access smooth, potentially non-convex functions through queries to an unbiased stochastic gradient oracle with bounded variance, we prove that (i…
Lower bounds on query complexity for reconstructing private learner's training data.
problem Query complexity of reconstructing private learner's training data.
method Minimax analysis, Rényi DP, Metric DP framework.
result First known lower bounds on adversary's query complexity for various DP learners.
BILBO optimizes bilevel problems without repeated lower-level optimizations.
problem Challenges in bilevel optimization, especially in noisy, constrained, and derivative-free settings.
method BILevel Bayesian Optimization (BILBO) that optimizes both levels simultaneously, using confidence-bounds and function query selection.
result Theoretical and empirical evidence of BILBO's effectiveness on various problems.
Overlapping clusters are common in models of many practical data-segmentation applications. Suppose we are given n n n elements to be clustered into k k k possibly overlapping clusters, and an oracle that can interactively answer queries of the form "do elements u u u and v v v belong to the same cluster?" The goal is to recov…
This paper explores the adaptive (active) PAC (probably approximately correct) top- k k k ranking (i.e., top- k k k item selection) and total ranking problems from l l l -wise ( l ≥ 2 l\geq 2 l ≥ 2 ) comparisons under the multinomial logit (MNL) model. By adaptively choosing sets to query and observing the noisy output of the most favored …
Hard problem of learning simple generative models from i.i.d. samples.
problem Learning simple neural network distributions from samples.
method Statistical query model, ODE-based construction of piecewise-linear functions.
result No polynomial-time algorithm can solve this problem even with one-hidden-layer ReLU networks.
Fairly allocate items with noisy queries, reducing envy.
problem Fairly allocate indivisible goods with unknown valuations.
method Use Gaussian noisy queries to find an envy-free allocation.
result The optimal number of queries scales as \( \frac{m^{2.5}}{Δ^2} \) for large negative-envy.
Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.
problem PAC learning γ-margin halfspaces with Random Classification Noise.
method Established an information-computation tradeoff and provided a simple efficient algorithm with sample complexity O(1/(γ^2 ε^2)). Also, proved lower bounds for SQ algorithms and low-degree polynomial tests.
result Inherent gap between sample complexity and computational efficiency for learning halfspaces with random noise.
New algorithms learn multi-index models via harmonic analysis, achieving statistical and computational trade-offs.
problem Learning multi-index models with unknown projections of input data.
method Exploiting the equivariance of the problem under the orthogonal group, we derive lower bounds and construct spectral algorithms based on harmonic tensor unfolding.
result Achieve statistical and computational trade-offs between sample and runtime complexity.
In adaptive data analysis, the user makes a sequence of queries on the data, where at each step the choice of query may depend on the results in previous steps. The releases are often randomized in order to reduce overfitting for such adaptively chosen queries. In this paper, we propose a minimax framework for adaptive…
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.
Optimal locally private hypothesis selection with interactive rounds.
problem Locally private hypothesis selection under i.i.d. samples.
method Developed an ε-LDP algorithm using critical queries for hypothesis selection.
result Achieved optimal sample complexity of Θ(k/α²ε²) for hypothesis selection.
We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex optimization, the sample complexity of our algorithms depends only on the margin of…