Searcharxiv⌕ Search

arXiv subjects

Konstantinos Stavropoulos

Publications and source records attributed to Konstantinos Stavropoulos.

At least 19 recordsLinked to original sources

Multiaccuracy as an Error Benchmark for Learning with Distribution Shift

Agnostic learning has a well-developed theory of computational and statistical complexity. For learning with distribution shift, even the choice of an appropriate error benchmark remains challenging. Testable learning with distribution shift (TDS) was introduced to develop computational foundations for this setting: using labeled training data and unlabeled test data, the learner must either produce a predictor with low test error or detect distribution shift. However, standard agnostic TDS guarantees allow a constant-factor amplification of the optimum error even when the training and test distributions coincide. They therefore do not directly recover the guarantee of classical agnostic learning. We introduce shift multiaccuracy, a stronger error benchmark inspired by multiaccuracy from algorithmic fairness. This yields a TDS formulation that becomes equivalent to multiaccuracy when there is no shift. Using a recent nontrivial reduction from agnostic learning to multiaccurate prediction from prior work, we obtain the first TDS framework that formally generalizes agnostic learning through an efficient reduction preserving the training marginal. The framework retains existing algorithmic upper bounds and inherits computational lower bounds from agnostic learning. Moreover, we establish a direct connection between our model and identity testing, yielding the first statistical characterization of agnostic TDS learning, in terms of Rademacher complexity. More broadly, we argue that shift multiaccuracy might be of independent interest in unsupervised domain adaptation, as it leads to sharper out-of-distribution generalization guarantees, and can be minimized directly, since its definition does not involve the unobserved test labels.

cs.LG↗

Efficient Robust Learning at the Information-Theoretic Limit

In an important recent work, Blanc (2026) gave an algorithm for robustly learning Boolean concept classes with respect to a fixed distribution that outputs a (randomized) classifier achieving the optimal error of $η+ \varepsilon$ where $η$ is the noise rate. In contrast, it is well known that deterministic hypotheses cannot achieve error less than $2η+ \varepsilon$. Blanc's algorithm is computationally inefficient, and the main problem left open in his work is to find a polynomial-time algorithm given access to an oracle for empirical risk minimization (ERM). Here we resolve this problem and give such an algorithm. Additionally, we give an efficient algorithm (no ERM oracle required) for robustly learning any function class that admits low-degree polynomial approximators with respect to hypercontractive distributions. This captures basic settings including halfspaces with respect to Gaussian marginals. Our techniques make new connections to various types of online convex optimization algorithms. As a surprising consequence, we show that efficient SQ learnability in the agnostic setting implies efficient learning with contamination (with respect to Gaussians or uniform over the hypercube).

cs.DS↗

Agnostic Learning by Imitating

Given a class of machine learning models and sample access to a data distribution with binary labels, which computational task is harder: training a discriminative model that distinguishes positive and negative labels as well as the best member of the class, or training a generative model whose outputs are indistinguishable from real data by all members of the class? We prove that these two fundamental tasks in computational learning theory are not just closely related, but actually equivalent to each other in complexity. One direction of this equivalence was previously known. Indeed, the powerful regularity lemma in complexity theory gives an efficient oracle reduction from the indistinguishability task (a.k.a. multiaccuracy) to the distinguishing task (a.k.a. agnostic learning) in the style of boosting algorithms. Our main contribution is an efficient oracle reduction in the other direction. Taking this idea further, we show that a multiaccuracy oracle is a remarkably powerful primitive, achieving not just agnostic learning but also a wide range of seemingly more demanding learning objectives via similarly efficient and direct constructions. Our results crucially use the power of making adaptive queries to the oracle, and stand in stark contrast to prior work, which showed that post-processing a single multiaccurate predictor is insufficient for even weak forms of learning. On a technical level, we draw a connection between our (offline) problem and a version of no-regret learning in the online setting, which allows us to use follow-the-leader type algorithms to modify the label distribution and aggregate the predictions of the multiaccuracy oracle.

cs.LG↗

Multigroup Fairness and Omniprediction: Separations and Equivalences

Omniprediction is a learning guarantee which requires a single predictor to be competitive relative to the best hypothesis from a benchmark class for any loss chosen from a family of loss functions. Loss Outcome Indistinguishability (loss OI for short) is a stronger notion that implies omniprediction. It requires the predicted distribution on labels to be indistinguishable from the true distribution to tests that depend on the loss functions and the benchmark class. Multiaccuracy and multicalibration are multigroup fairness notions that generalize classical notions of calibration and accuracy in expectation. Most known learning algorithms for omniprediction (both for the standard notion and for strengthenings like loss OI) rely on some version of these multigroup fairness notions, or on an intermediate notion called calibrated multiaccuracy. We ask if this is necessary: Does omniprediction require some form of multigroup fairness? We show that the answer is no for (plain) omniprediction, and yes for loss OI. First, a sequence of works shows that multicalibration or calibrated multiaccuracy imply omniprediction. We rule out even a weak converse, by showing that omniprediction for proper losses does not imply even accuracy in expectation, a much weaker notion than any of calibration, multiaccuracy, or multicalibration. Second, prior work showed how to achieve loss OI from a combination of calibration and multiaccuracy. We show a converse: loss OI is equivalent to a form of calibrated multiaccuracy.

cs.LG↗

Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension

In traditional models of supervised learning, the goal of a learner-- given examples from an arbitrary joint distribution on $\mathbb{R}^d \times \{\pm 1\}$-- is to output a hypothesis that is competitive (to within $ε$) of the best fitting concept from some class. In order to escape strong hardness results for learning even simple concept classes, we introduce a smoothed-analysis framework that requires a learner to compete only with the best classifier that is robust to small random Gaussian perturbation. This subtle change allows us to give a wide array of learning results for any concept that (1) depends on a low-dimensional subspace (aka multi-index model) and (2) has a bounded Gaussian surface area. This class includes functions of halfspaces and (low-dimensional) convex sets, cases that are only known to be learnable in non-smoothed settings with respect to highly structured distributions such as Gaussians. Our definition of smoothed agnostic learning is an interpolation between the case where the instance distribution $D$ and the optimal classifier can be arbitrarily coupled (which corresponds to agnostic learning and $σ= 0$) and completely decoupled (when $σ= \infty$). This decoupling allows us to avoid worst-case concepts that can encode complexity-theoretic primitives. Surprisingly, our analysis also yields new results for traditional non-smoothed frameworks such as learning with margin. In particular, we obtain the first algorithm for agnostically learning intersections of $k$-halfspaces in time $k^{\mathrm{poly}(\frac{\log k}{εγ}) }$ where $γ$ is the margin parameter. Before our work, the best-known runtime was exponential in $k$ (Arriaga and Vempala, FOCS' 99).

cs.LG↗

Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift

Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al. (2024)). Algorithms for TDS learning are allowed to reject a test set entirely if distribution shift is detected. In contrast, PQ learners may only reject points that are deemed out-of-distribution on an individual basis. Our main result is a surprising equivalence between these two models in the distribution-free setting. In particular, we give an efficient black-box reduction from PQ learning to TDS learning for any Boolean concept class. This equivalence implies the first hardness results for distribution-free TDS learning of basic classes such as halfspaces. The main technical contribution underlying our equivalence is a method for boosting, via branching programs, the weak distinguishing power of TDS learners that have rejected the target domain. We also show that giving a learner access to membership queries sidesteps these hardness results and allows for efficient, distribution-free PQ learnability of halfspaces. Our algorithm iteratively recovers large-margin separators obtained by applying successive Forster transforms on the training data.

cs.DS↗

Iterative Chow Filtering for Learning with Distribution Shift

Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make correct predictions on the test set but is allowed to abstain from predicting on out-of-distribution points. Their results rely on ${\cal L}_2$ sandwiching approximations, a strong requirement that leads to poor bounds for several basic function classes such as DNF formulas. Here, we show that the weaker notion of ${\cal L}_1$ sandwiching suffices for efficient PQ learning. As a consequence, we obtain the first quasipolynomial-time PQ learning algorithm for DNFs under the uniform distribution and essentially match the guarantees known for ordinary PAC learning. More broadly, our bounds provide exponential improvements for several classes including constant depth circuits and constant degree polynomial threshold functions. Our main technical ingredient is Iterative Chow Filtering, a new procedure that uses low-degree Chow parameters to identify and remove test points incompatible with the training distribution.

cs.DS↗

Testing Noise Assumptions of Learning Algorithms

We pose a fundamental question in computational learning theory: can we efficiently test whether a training set satisfies the assumptions of a given noise model? This question has remained unaddressed despite decades of research on learning in the presence of noise. In this work, we show that this task is tractable and present the first efficient algorithm to test various noise assumptions on the training data. To model this question, we extend the recently proposed testable learning framework of Rubinfeld and Vasilyan (2023) and require a learner to run an associated test that satisfies the following two conditions: (1) whenever the test accepts, the learner outputs a classifier along with a certificate of optimality, and (2) the test must pass for any dataset drawn according to a specified modeling assumption on both the marginal distribution and the noise model. We then consider the problem of learning halfspaces over Gaussian marginals with Massart noise (where each label can be flipped with probability less than $1/2$ depending on the input features), and give a fully-polynomial time testable learning algorithm. We also show a separation between the classical setting of learning in the presence of structured noise and testable learning. In fact, for the simple case of random classification noise (where each label is flipped with fixed probability $η= 1/2$), we show that testable learning requires super-polynomial time while classical learning is trivial.

cs.LG↗

The Importance of Being Smoothly Calibrated

Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. We generalize, unify, and extend previous results on smooth calibration, both as a robust calibration measure, and as a step towards omniprediction, which enables predictions with low regret for downstream decision makers seeking to optimize some proper loss unknown to the predictor. We present a new omniprediction guarantee for smoothly calibrated predictors, for the class of all bounded proper losses. We smooth the predictor by adding some noise to it, and compete against smoothed versions of any benchmark predictor on the space, where we add some noise to the predictor and then post-process it arbitrarily. The omniprediction error is bounded by the smooth calibration error of the predictor and the earth mover's distance from the benchmark. We exhibit instances showing that this dependence cannot, in general, be improved. We show how this unifies and extends prior results [Foster and Vohra, 1998; Hartline, Wu, and Yang, 2025] on omniprediction from smooth calibration. We present a crisp new characterization of smooth calibration in terms of the earth mover's distance to the closest perfectly calibrated joint distribution of predictions and labels. This also yields a simpler proof of the relation to the lower distance to calibration from [Blasiok, Gopalan, Hu, and Nakkiran, 2023]. We use this to show that the upper distance to calibration cannot be estimated within a quadratic factor with sample complexity independent of the support size of the predictions. This is in contrast to the distance to calibration, where the corresponding problem was known to be information-theoretically impossible: no finite number of samples suffice [Blasiok, Gopalan, Hu, and Nakkiran, 2023].

cs.LG↗

Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension

Recent work has shown the surprising power of low-degree sandwiching polynomial approximators in the context of challenging learning settings such as learning with distribution shift, testable learning, and learning with contamination. A pair of sandwiching polynomials approximate a target function in expectation while also providing pointwise upper and lower bounds on the function's values. In this paper, we give a new method for constructing low-degree sandwiching polynomials that yield greatly improved degree bounds for several fundamental function classes and marginal distributions. In particular, we obtain degree $\mathrm{poly}(k)$ sandwiching polynomials for functions of $k$ halfspaces under the Gaussian distribution, improving exponentially over the prior $2^{O(k)}$ bound. More broadly, our approach applies to function classes that are low-dimensional and have smooth boundary. In contrast to prior work, our proof is relatively simple and directly uses the smoothness of the target function's boundary to construct sandwiching Lipschitz functions, which are amenable to results from high-dimensional approximation theory. For low-dimensional polynomial threshold functions (PTFs) with respect to Gaussians, we obtain doubly exponential improvements without applying the FT-mollification method of Kane used in the best previous result.

cs.LG↗

Hamiltonicity in generalized quasi-dihedral groups

Witte Morris showed in [21] that every connected Cayley graph of a finite (generalized) dihedral group has a Hamiltonian path. The infinite dihedral group is defined as the free product with amalgamation $\mathbb Z_2 \ast \mathbb Z_2$. We show that every connected Cayley graph of the infinite dihedral group has both a Hamiltonian double ray, and extend this result to all two-ended generalized quasi-dihedral groups.

math.CO↗

The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination

Inspired by recent work on learning with distribution shift, we give a general outlier removal algorithm called iterative polynomial filtering and show a number of striking applications for supervised learning with contamination: (1) We show that any function class that can be approximated by low-degree polynomials with respect to a hypercontractive distribution can be efficiently learned under bounded contamination (also known as nasty noise). This is a surprising resolution to a longstanding gap between the complexity of agnostic learning and learning with contamination, as it was widely believed that low-degree approximators only implied tolerance to label noise. In particular, it implies the first efficient algorithm for learning halfspaces with $η$-bounded contamination up to error $2η+ε$ with respect to the Gaussian distribution. (2) For any function class that admits the (stronger) notion of sandwiching approximators, we obtain near-optimal learning guarantees even with respect to heavy additive contamination, where far more than $1/2$ of the training set may be added adversarially. Prior related work held only for regression and in a list-decodable setting. (3) We obtain the first efficient algorithms for tolerant testable learning of functions of halfspaces with respect to any fixed log-concave distribution. Even the non-tolerant case for a single halfspace in this setting had remained open. These results significantly advance our understanding of efficient supervised learning under contamination, a setting that has been much less studied than its unsupervised counterpart.

cs.LG↗

Efficient Calibration for Decision Making

A decision-theoretic characterization of perfect calibration is that an agent seeking to minimize a proper loss in expectation cannot improve their outcome by post-processing a perfectly calibrated predictor. Hu and Wu (FOCS'24) use this to define an approximate calibration measure called calibration decision loss ($\mathsf{CDL}$), which measures the maximal improvement achievable by any post-processing over any proper loss. Unfortunately, $\mathsf{CDL}$ turns out to be intractable to even weakly approximate in the offline setting, given black-box access to the predictions and labels. We suggest circumventing this by restricting attention to structured families of post-processing functions $K$. We define the calibration decision loss relative to $K$, denoted $\mathsf{CDL}_K$ where we consider all proper losses but restrict post-processings to a structured family $K$. We develop a comprehensive theory of when $\mathsf{CDL}_K$ is information-theoretically and computationally tractable, and use it to prove both upper and lower bounds for natural classes $K$. In addition to introducing new definitions and algorithmic techniques to the theory of calibration for decision making, our results give rigorous guarantees for some widely used recalibration procedures in machine learning.

cs.LG↗

A Fully Polynomial-Time Algorithm for Robustly Learning Halfspaces over the Hypercube

We give the first fully polynomial-time algorithm for learning halfspaces with respect to the uniform distribution on the hypercube in the presence of contamination, where an adversary may corrupt some fraction of examples and labels arbitrarily. We achieve an error guarantee of $η^{O(1)}+ε$ where $η$ is the noise rate. Such a result was not known even in the agnostic setting, where only labels can be adversarially corrupted. All prior work over the last two decades has a superpolynomial dependence in $1/ε$ or succeeds only with respect to continuous marginals (such as log-concave densities). Previous analyses rely heavily on various structural properties of continuous distributions such as anti-concentration. Our approach avoids these requirements and makes use of a new algorithm for learning Generalized Linear Models (GLMs) with only a polylogarithmic dependence on the activation function's Lipschitz constant. More generally, our framework shows that supervised learning with respect to discrete distributions is not as difficult as previously thought.

cs.DS↗

Sparse Linear Regression is Easy on Random Supports

Sparse linear regression is one of the most basic questions in machine learning and statistics. Here, we are given as input a design matrix $X \in \mathbb{R}^{N \times d}$ and measurements or labels ${y} \in \mathbb{R}^N$ where ${y} = {X} {w}^* + ξ$, and $ξ$ is the noise in the measurements. Importantly, we have the additional constraint that the unknown signal vector ${w}^*$ is sparse: it has $k$ non-zero entries where $k$ is much smaller than the ambient dimension. Our goal is to output a prediction vector $\widehat{w}$ that has small prediction error: $\frac{1}{N}\cdot \|{X} {w}^* - {X} \widehat{w}\|^2_2$. Information-theoretically, we know what is best possible in terms of measurements: under most natural noise distributions, we can get prediction error at most $ε$ with roughly $N = O(k \log d/ε)$ samples. Computationally, this currently needs $d^{Ω(k)}$ run-time. Alternately, with $N = O(d)$, we can get polynomial-time. Thus, there is an exponential gap (in the dependence on $d$) between the two and we do not know if it is possible to get $d^{o(k)}$ run-time and $o(d)$ samples. We give the first generic positive result for worst-case design matrices ${X}$: For any ${X}$, we show that if the support of ${w}^*$ is chosen at random, we can get prediction error $ε$ with $N = \text{poly}(k, \log d, 1/ε)$ samples and run-time $\text{poly}(d,N)$. This run-time holds for any design matrix ${X}$ with condition number up to $2^{\text{poly}(d)}$. Previously, such results were known for worst-case ${w}^*$, but only for random design matrices from well-behaved families, matrices that have a very low condition number ($\text{poly}(\log d)$; e.g., as studied in compressed sensing), or those with special structural properties.

cs.LG↗

Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees

We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives labeled examples from a training distribution and unlabeled examples from a test distribution and must either output a hypothesis with low test error or reject if distribution shift is detected. No assumptions are made on the test distribution. All prior work in TDS learning focuses on classification, while here we must handle the setting of nonconvex regression. Our results apply to real-valued networks with arbitrary Lipschitz activations and work whenever the training distribution has strictly sub-exponential tails. For training distributions that are bounded and hypercontractive, we give a fully polynomial-time algorithm for TDS learning one hidden-layer networks with sigmoid activations. We achieve this by importing classical kernel methods into the TDS framework using data-dependent feature maps and a type of kernel matrix that couples samples from both train and test distributions.

cs.DS↗

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

We study the problem of PAC learning $γ$-margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetilde{O}((εγ)^{-2})$ and achieves classification error at most $η+ε$ where $η$ is the Massart noise rate. Prior works [DGT19,CKMY20] came with worse sample complexity guarantees (in both $ε$ and $γ$) or could only handle random classification noise [DDK+23,KIT+23] -- a much milder noise assumption. We also show that our results extend to the more challenging setting of learning generalized linear models with a known link function under Massart noise, achieving a similar sample complexity to the halfspace case. This significantly improves upon the prior state-of-the-art in this setting due to [CKMY20], who introduced this model.

cs.LG↗

Learning Constant-Depth Circuits in Malicious Noise Models

The seminal work of Linial, Mansour, and Nisan gave a quasipolynomial-time algorithm for learning constant-depth circuits ($\mathsf{AC}^0$) with respect to the uniform distribution on the hypercube. Extending their algorithm to the setting of malicious noise, where both covariates and labels can be adversarially corrupted, has remained open. Here we achieve such a result, inspired by recent work on learning with distribution shift. Our running time essentially matches their algorithm, which is known to be optimal assuming various cryptographic primitives. Our proof uses a simple outlier-removal method combined with Braverman's theorem for fooling constant-depth circuits. We attain the best possible dependence on the noise rate and succeed in the harshest possible noise model (i.e., contamination or so-called "nasty noise").

cs.DS↗