论文检索

Theory/Learning Theory

Peter Dixon, A. Pavan, Jason Vander Woude, N. V. Vinodchandran

We investigate replicable learning algorithms. Informally a learning algorithm is replicable if the algorithm outputs the same canonical hypothesis over multiple runs with high probability, even when different runs observe a different set of samples from the unknown data distribution. In general, such a strong notion of replicability is not achievable. Thus we consider two feasible notions of replicability called {\em list replicability} and {\em certificate replicability}. Intuitively, these notions capture the degree of (non) replicability. The goal is to design learning algorithms with optimal list and certificate complexities while minimizing the sample complexity. Our contributions are the following.1. We first study the learning task of estimating the biases of $d$ coins, up to an additive error of $\varepsilon$, by observing samples. For this task, we design a $(d+1)$-list replicable algorithm. To complement this result, we establish that the list complexity is optimal, i.e there are no learning algorithms with a list size smaller than $d+1$ for this task. We also design learning algorithms with certificate complexity $\tilde{O}(\log d)$. The sample complexity of both these algorithms is $\tilde{O}(\frac{d^2}{\varepsilon^2})$ where $\varepsilon$ is the approximation error parameter (for a constant error probability). 2. In the PAC model, we show that any hypothesis class that is learnable with $d$-nonadaptive statistical queries can be learned via a $(d+1)$-list replicable algorithm and also via a $\tilde{O}(\log d)$-certificate replicable algorithm. The sample complexity of both these algorithms is $\tilde{O}(\frac{d^2}{\nu^2})$ where $\nu$ is the approximation error of the statistical query. We also show that for the concept class \dtep, the list complexity is exactly $d+1$ with respect to the uniform distribution. To establish our upper bound results we use rounding schemes induced by geometric partitions with certain properties. We use Sperner/KKM Lemma to establish the lower bound results.

Theory/Learning Theory

Vasilis Kontonis, Mingchen Ma, Christos Tzamos

We study fixed-design online learning where the learner is allowed to choose the order of the datapoints in order to minimize their regret (aka self-directed online learning). We focus on the fundamental task of online linear regression: the learner is given a dataset $X$ with $n$ examples in $d$ dimensions and at step $t$ they select a point $x_t \in X$, predict a value $\widetilde y_t$, and suffer loss $(\widetilde y_t - w^\ast \cdot x_t)^2$. The goal is to design algorithms that order the examples and achieve better regret than random- or worst-order online algorithms.For an arbitrary dataset $X$, we show that, under the Exponential Time Hypothesis, no efficient algorithm can approximate the optimal (best-order) regret within a factor of $d^{1/\poly(\log \log d)}$.We then show that, for structured datasets, we can bypass the above hardness result and achieve nearly optimal regret. When the examples of $X$ are drawn i.i.d.\ from the uniform distribution on the sphere, we present an algorithm based on the greedy heuristic of selecting ``easiest'' examples first that achieves a $\log d$-approximation of the optimal regret.

Theory/Learning Theory

Apoorva Sharma, Sushant Veer, Asher Hancock, Heng Yang, Marco Pavone, Anirudha Majumdar

Inductive Conformal Prediction (ICP) provides a practical and effective approach for equipping deep learning models with uncertainty estimates in the form of set-valued predictions which are guaranteed to contain the ground truth with high probability.Despite the appeal of this coverage guarantee, these sets may not be efficient: the size and contents of the prediction sets are not directly controlled, and instead depend on the underlying model and choice of score function.To remedy this, recent work has proposed learning model and score function parameters using data to directly optimize the efficiency of the ICP prediction sets.While appealing, the generalization theory for such an approach is lacking: direct optimization of empirical efficiency may yield prediction sets that are either no longer efficient on test data, or no longer obtain the required coverage on test data.In this work, we use PAC-Bayes theory to obtain generalization bounds on both the coverage and the efficiency of set-valued predictors which can be directly optimized to maximize efficiency while satisfying a desired test coverage.In contrast to prior work, our framework allows us to utilize the entire calibration dataset to learn the parameters of the model and score function, instead of requiring a separate hold-out set for obtaining test-time coverage guarantees.We leverage these theoretical results to provide a practical algorithm for using calibration data to simultaneously fine-tune the parameters of a model and score function while guaranteeing test-time coverage and efficiency of the resulting prediction sets.We evaluate the approach on regression and classification tasks, and outperform baselines calibrated using a Hoeffding bound-based PAC guarantee on ICP, especially in the low-data regime.

Theory/Learning Theory

Anqi Mao, Mehryar Mohri, Yutao Zhong

We present an extensive study of surrogate losses for structured prediction supported by *$H$-consistency bounds*. These are recently introduced guarantees that are more relevant to learning than Bayes-consistency, since they are not asymptotic and since they take into account the hypothesis set $H$ used. We first show that no non-trivial $H$-consistency bound can be derived for widely used surrogate structured prediction losses. We then define several new families of surrogate losses, including *structured comp-sum losses* and *structured constrained losses*, for which we prove $H$-consistency bounds and thus Bayes-consistency. These loss functions readily lead to new structured prediction algorithms with stronger theoretical guarantees, based on their minimization. We describe efficient algorithms for minimizing several of these surrogate losses, including a new *structured logistic loss*.

Theory/Learning Theory

Shivam Gupta, Jasper Lee, Eric Price, Paul Valiant

Location estimation is one of the most basic questions in parametric statistics. Suppose we have a known distribution density $f$, and we get $n$ i.i.d. samples from $f(x-\mu)$ for some unknown shift $\mu$.The task is to estimate $\mu$ to high accuracy with high probability.The maximum likelihood estimator (MLE) is known to be asymptotically optimal as $n \to \infty$, but what is possible for finite $n$?In this paper, we give two location estimators that are optimal under different criteria: 1) an estimator that has minimax-optimal estimation error subject to succeeding with probability $1-\delta$ and 2) a confidence interval estimator which, subject to its output interval containing $\mu$ with probability at least $1-\delta$, has the minimum expected squared interval width among all shift-invariant estimators.The latter construction can be generalized to minimizing the expectation of any loss function on the interval width.

Theory/Learning Theory

Ilias Diakonikolas, Daniel Kane, Lisheng Ren, Yuxin Sun

We study the complexity of Non-Gaussian Component Analysis (NGCA) in the Statistical Query (SQ) model.Prior work developed a methodology to prove SQ lower bounds for NGCA that have been applicable to a wide range of contexts.In particular, it was known that for any univariate distribution $A$ satisfying certain conditions,distinguishing between a standard multivariate Gaussian and a distribution that behaves like $A$ in a random hidden direction and like a standard Gaussian in the orthogonal complement, is SQ-hard.The required conditions were that (1) $A$ matches many low-order moments with a standard Gaussian,and (2) the chi-squared norm of $A$ with respect to the standard Gaussian is finite.While the moment-matching condition is clearly necessary for hardness, the chi-squared condition was only required for technical reasons.In this work, we establish that the latter condition is indeed not necessary.In particular, we prove near-optimal SQ lower bounds for NGCA under the moment-matching condition only.

Theory/Learning Theory

Nika Haghtalab, Michael Jordan, Eric Zhao

We provide a unifying framework for the design and analysis of multi-calibrated predictors. By placing the multi-calibration problem in the general setting of multi-objective learning---where learning guarantees must hold simultaneously over a set of distributions and loss functions---we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as error tolerances that scale with the square-root of group size versus the constant tolerances guaranteed by prior works, and improving the complexity of $k$-class multi-calibration by an exponential factor of $k$ versus Gopalan et al.. Beyond multi-calibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

Theory/Learning Theory

Aravind Gollakota, Parikshit Gopalan, Adam Klivans, Konstantinos Stavropoulos

We give the first result for agnostically learning Single-Index Models (SIMs) with arbitrary monotone and Lipschitz activations. All prior work either held only in the realizable setting or required the activation to be known. Moreover, we only require the marginal to have bounded second moments, whereas all prior work required stronger distributional assumptions (such as anticoncentration or boundedness). Our algorithm is based on recent work by Gopalan et al. [2023] on Omniprediction using predictors satisfying calibrated multiaccuracy. Our analysis is simple and relies on the relationship between Bregman divergences (or matching losses) and $\ell_p$ distances. We also provide new guarantees for standard algorithms like GLMtron and logistic regression in the agnostic setting.

Theory/Learning Theory

Gil Kur, Eli Putterman, Alexander Rakhlin

It is well known that Empirical Risk Minimization (ERM) may attain minimax suboptimal rates in terms of the mean squared error (Birgé and Massart, 1993). In this paper, we prove that, under relatively mild assumptions, the suboptimality of ERM must be due to its bias. Namely, the variance error term of ERM (in terms of the bias and variance decomposition) enjoys the minimax rate. In the fixed design setting, we provide an elementary proof of this result using the probabilistic method. Then, we extend our proof to the random design setting for various models. In addition, we provide a simple proof of Chatterjee’s admissibility theorem (Chatterjee, 2014, Theorem 1.4), which states that in the fixed design setting, ERM cannot be ruled out as an optimal method, and then we extend this result to the random design setting. We also show that our estimates imply stability of ERM, complementing the main result of Caponnetto and Rakhlin (2006) for non-Donsker classes. Finally, we highlight the somewhat irregular nature of the loss landscape of ERM in the non-Donsker regime, by showing that functions can be close to ERM, in terms of $L_2$ distance, while still being far from almost-minimizers of the empirical loss.

Theory/Learning Theory

Anqi Mao, Christopher Mohri, Mehryar Mohri, Yutao Zhong

We study a two-stage scenario for learning to defer with multiple experts, which is crucial in practice for many applications. In this scenario, a predictor is derived in a first stage by training with a common loss function such as cross-entropy. In the second stage, a deferral function is learned to assign the most suitable expert to each input. We design a new family of surrogate loss functions for this scenario both in the score-based and the predictor-rejector settings and prove that they are supported by $H$-consistency bounds, which implies their Bayes-consistency. Moreover, we show that, for a constant cost function, our two-stage surrogate losses are realizable $H$-consistent. While the main focus of this work is a theoretical analysis, we also report the results of several experiments on CIFAR-10 and SVHN datasets.

Theory/Learning Theory

Gleb Novikov, David Steurer, Stefan Tiegel

We study the problem of robustly estimating the mean or location parameter without moment assumptions.Known computationally efficient algorithms rely on strong distributional assumptions, such as sub-Gaussianity, or (certifiably) bounded moments.Moreover, the guarantees that they achieve in the heavy-tailed setting are weaker than those for sub-Gaussian distributions with known covariance.In this work, we show that such a tradeoff, between error guarantees and heavy-tails, is not necessary for symmetric distributions.We show that for a large class of symmetric distributions, the same error as in the Gaussian setting can be achieved efficiently.The distributions we study include products of arbitrary symmetric one-dimensional distributions, such as product Cauchy distributions, as well as elliptical distributions, a vast generalization of the Gaussian distribution.For product distributions and elliptical distributions with known scatter (covariance) matrix, we show that given an $\varepsilon$-corrupted sample, we can with probability at least $1-\delta$ estimate its location up to error $O(\varepsilon \sqrt{\log(1/\varepsilon)})$ using $\tfrac{d\log(d) + \log(1/\delta)}{\varepsilon^2 \log(1/\varepsilon)}$ samples.This result matches the best-known guarantees for the Gaussian distribution and known SQ lower bounds (up to the $\log(d)$ factor).For elliptical distributions with unknown scatter (covariance) matrix, we propose a sequence of efficient algorithms that approaches this optimal error.Specifically, for every $k \in \mathbb{N}$, we design an estimator using time and samples $\tilde{O}({d^k})$ achieving error $O(\varepsilon^{1-\frac{1}{2k}})$.This matches the error and running time guarantees when assuming certifiably bounded moments of order up to $k$.For unknown covariance, such error bounds of $o(\sqrt{\varepsilon})$ are not even known for (general) sub-Gaussian distributions.Our algorithms are based on a generalization of the well-known filtering technique [DK22].More specifically, we show how this machinery can be combined with Huber-loss-based techniques to work with projections of the noise that behave more nicely than the initial noise.Moreover, we show how sum-of-squares proofs can be used to obtain algorithmic guarantees even for distributions without a first moment.We believe that this approach may find other applications in future works.

Theory/Learning Theory

Moshe Shenfeld, Katrina Ligett

Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting, wherein the empirical evaluation of queries on the sample significantly deviates from their mean with respect to the underlying data distribution. It turns out that simple noise addition algorithms suffice to prevent this issue, and differential privacy-based analysis of these algorithms shows that they can handle an asymptotically optimal number of queries. However, differential privacy's worst-case nature entails scaling such noise to the range of the queries even for highly-concentrated queries, or introducing more complex algorithms.In this paper, we prove that straightforward noise-addition algorithms already provide variance-dependent guarantees that also extend to unbounded queries. This improvement stems from a novel characterization that illuminates the core problem of adaptive data analysis. We show that the harm of adaptivity results from the covariance between the new query and a Bayes factor-based measure of how much information about the data sample was encoded in the responses given to past queries. We then leverage this characterization to introduce a new data-dependent stability notion that can bound this covariance.

Theory/Learning Theory

Alessio Mazzetto, Eli Upfal

We develop and analyze a general technique for learning with an unknown distribution drift. Given a sequence of independent observations from the last $T$ steps of a drifting distribution, our algorithm agnostically learns a family of functions with respect to the current distribution at time $T$. Unlike previous work, our technique does not require prior knowledge about the magnitude of the drift. Instead, the algorithm adapts to the sample data. Without explicitly estimating the drift, the algorithm learns a family of functions with almost the same error as a learning algorithm that knows the magnitude of the drift in advance. Furthermore, since our algorithm adapts to the data, it can guarantee a better learning error than an algorithm that relies on loose bounds on the drift. We demonstrate the application of our technique in two fundamental learning scenarios: binary classification and linear regression.

Theory/Learning Theory

Chenyu Zheng, Guoqiang Wu, Chongxuan LI

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot learning, and adversarially robust learning. However, little work has theoretically investigated the effect of generative data augmentation. To fill this gap, we establish a general stability bound in this not independently and identicallydistributed (non-i.i.d.) setting, where the learned distribution is dependent on the original train set and generally not the same as the true distribution. Our theoretical result includes the divergence between the learned distribution and the true distribution. It shows that generative data augmentation can enjoy a faster learning rate when the order of divergence term is $o(\max\left( \log(m)\beta_m, 1 / \sqrt{m})\right)$, where $m$ is the train set size and $\beta_m$ is the corresponding stability constant. We further specify the learning setup to the Gaussian mixture model and generative adversarial nets. We prove that in both cases, though generative data augmentation does not enjoy a faster learning rate, it can improve the learning guarantees at a constant level when the train set is small, which is significant when the awful overfitting occurs. Simulation results on the Gaussian mixture model and empirical results on generative adversarial nets support our theoretical conclusions.

Theory/Learning Theory

Riccardo Giuseppe Margiotta, Sebastian Goldt, Guido Sanguinetti

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large literature has studied the case of test-time attacks on pre-trained models, the important case of attacks in an online learning setting has received little attention so far. In this work, we use a control-theoretical perspective to study the scenario where an attacker may perturb data labels to manipulate the learning dynamics of an online learner. We perform a theoretical analysis of the problem in a teacher-student setup, considering different attack strategies, and obtaining analytical results for the steady state of simple linear learners. These results enable us to prove that a discontinuous transition in the learner's accuracy occurs when the attack strength exceeds a critical threshold. We then study empirically attacks on learners with complex architectures using real data, confirming the insights of our theoretical analysis. Our findings show that greedy attacks can be extremely efficient, especially when data stream in small batches.

Theory/Learning Theory

Guy Kornowski, Steve Hanneke, Aryeh Kontorovich

We generalize the notion of average Lipschitz smoothness proposed by Ashlagi et al. (COLT 2021) by extending it to Hölder smoothness. This measure of the "effective smoothness" of a function is sensitive to the underlying distribution and can be dramatically smaller than its classic "worst-case" Hölder constant.We consider both the realizable and the agnostic (noisy) regression settings, proving upper and lower risk bounds in terms of the average Hölder smoothness; these rates improve upon both previously known rates even in the special case of average Lipschitz smoothness.Moreover, our lower bound is tight in the realizable setting up to log factors, thus we establish the minimax rate.From an algorithmic perspective, since our notion of average smoothness is defined with respect to the unknown underlying distribution, the learner does not have an explicit representation of the function class, hence is unable to execute ERM. Nevertheless, we provide distinct learning algorithms that achieve both (nearly) optimal learning rates.Our results hold in any totally bounded metric space, and are stated in terms of its intrinsic geometry.Overall, our results show that the classic worst-case notion of Hölder smoothness can be essentially replaced by its average, yielding considerably sharper guarantees.

Theory/Learning Theory

Constantine Caramanis, Dimitris Fotakis, Alkis Kalavasis, Vasilis Kontonis, Christos Tzamos

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network is used as a solution generator which is then trained by gradient-based methods (e.g., policy gradient) to successively obtain better solution distributions.In this work we introduce a novel theoretical framework for analyzing the effectiveness of such methods. We ask whether there exist generative models that (i) are expressive enough to generate approximately optimal solutions; (ii) have a tractable, i.e, polynomial in the size of the input, number of parameters; (iii) their optimization landscape is benign in the sense that it does not contain sub-optimal stationary points. Our main contribution is a positive answer to this question. Our result holds for a broad class of combinatorial problems including Max- and Min-Cut, Max-$k$-CSP, Maximum-Weight-Bipartite-Matching, and the Traveling Salesman Problem. As a byproduct of our analysis we introduce a novel regularization process over vanilla gradient descent and provide theoretical and experimental evidence that it helps address vanishing-gradient issues and escape bad stationary points.

Theory/Learning Theory

Yang Sui, Xin HE, Yang Bai

In this paper, we design a regularization-free algorithm for high-dimensional support vector machines (SVMs) by integrating over-parameterization with Nesterov's smoothing method, and provide theoretical guarantees for the induced implicit regularization phenomenon. In particular, we construct an over-parameterized hinge loss function and estimate the true parameters by leveraging regularization-free gradient descent on this loss function. The utilization of Nesterov's method enhances the computational efficiency of our algorithm, especially in terms of determining the stopping criterion and reducing computational complexity. With appropriate choices of initialization, step size, and smoothness parameter, we demonstrate that unregularized gradient descent achieves a near-oracle statistical convergence rate. Additionally, we verify our theoretical findings through a variety of numerical experiments and compare the proposed method with explicit regularization. Our results illustrate the advantages of employing implicit regularization via gradient descent in conjunction with over-parameterization in sparse SVMs.

Theory/Learning Theory

Srinivasan Arunachalam, Vojtech Havlicek, Louis Schatzki

In this work we make progress in understanding the relationship between learning models when given access to entangled measurements, separable measurements and statistical measurements in the quantum statistical query ($\mathsf{QSQ}$) model. To this end, we show the following results.$\textbf{Entanglement versus separable measurements.}$ The goal here is to learn an unknown $f$ from the concept class $\mathcal{C} \subseteq \{f:\{0,1\}^n\rightarrow [k]\}$ given copies of $\frac{1}{\sqrt{2^n}}\sum_x \ket{x,f(x)}$. We show that, if $T$ copies suffice to learn $f$ using entangled measurements, then $O(nT^2)$ copies suffice to learn $f$ using just separable measurements. Additionally, we exhibit a concept class $\mathcal{C}$ for which, in order to learn some \emph{property} of $f$, the sample complexity of learning using entangled measurements is exponentially smaller than separable measurements.$\textbf{Entangled versus statistical measurements}$ The goal here is to learn a function $f \in \mathcal{C}$ given access to separable measurements and statistical measurements. We exhibit a concept class $\mathcal{C}$ based on degree-$2$ functions that gives an exponential separation between $\mathsf{QSQ}$ learning and quantum learning with entangled measurements (even in the presence of noise). This proves the "quantum analogue" of the seminal result of (Blum, 2003) that separates classical $\mathsf{SQ}$ learning from classical $\mathsf{PAC}$ learning with classification~noise.$\textbf{$\mathsf{QSQ}$ lower bounds for learning states.}$ The main technical contribution is to introduce a quantum statistical query dimension ($\mathsf{QSDA}$), which we use to give lower bounds on the $\mathsf{QSQ}$ complexity of learning. Using this, we prove exponential $\mathsf{QSQ}$ lower bounds for testing purity of quantum states, learning CCHL states, coset states of Abelian groups, degree-$2$ functions, planted bi-clique states and learning output states of Clifford circuits of depth polylog($n$).$\textbf{Further applications.}$ Using our $\mathsf{QSQ}$ lower bounds give an $\textit{unconditional}$ separation between weak and strong error mitigation and prove lower bounds for learning distributions in the $\mathsf{QSQ}$ model. Prior works by (Quek et al., 2022), (Hinsche et al., 2022), and (Neitner et al., 23) proved the analogous results $\textit{assuming}$ diagonal measurements and our work removes this assumption.

Theory/Learning Theory

Nataly Brukhim, Amit Daniely, Yishay Mansour, Shay Moran

We study a generalization of boosting to the multiclass setting.We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being “slightly better than random guessing”. We give a simple and efficient boosting algorithm, that does not require realizability assumptions and its sample and oracle complexity bounds are independent of the number of classes. In addition, we utilize our new boosting technique in several theoretical applications within the context of List PAC Learning. First, we establish an equivalence to weak PAC learning. Furthermore, we present a new result on boosting for list learners, as well as provide a novel proof for the characterization of multiclass PAC learning and List PAC learning. Notably, our technique gives rise to simplified algorithms and analysis compared to previous works.