论文检索

Theory/Learning Theory

Anqi Mao, Mehryar Mohri, Yutao Zhong

A series of recent publications by Awasthi et al. have introduced the key notion of *$H$-consistency bounds* for surrogate loss functions. These are upper bounds on the zero-one estimation error of any predictor in a hypothesis set, expressed in terms of its surrogate loss estimation error. They are both non-asymptotic and hypothesis set-specific and thus stronger and more informative than Bayes-consistency. However, determining if they hold and deriving these bounds have required a specific proof and analysis for each surrogate loss. Can we derive more general tools and characterizations? This paper provides both a general characterization and an extension of $H$-consistency bounds for multi-class classification. We present new and tight $H$-consistency bounds for both the family of constrained losses and that of comp-sum losses, which covers the familiar cross-entropy, or logistic loss applied to the outputs of a neural network. We further extend our analysis beyond the completeness assumptions adopted in previous studies and cover more realistic bounded hypothesis sets. Our characterizations are based on error transformations, which are explicitly defined for each formulation. We illustrate the application of our general results through several special examples. A by-product of our analysis is the observation that a recently derived multi-class $H$-consistency bound for cross-entropy reduces to an excess bound and is not significant. Instead, we prove a much stronger and more significant guarantee.

Theory/Learning Theory

Kaifu Wang, Efthymia Tsamoura, Dan Roth

We consider a weakly supervised learning scenario where the supervision signal is generated by a transition function $\sigma$ of labels associated with multiple input instances. We formulate this problem as *multi-instance Partial Label Learning (multi-instance PLL)*, which is an extension to the standard PLL problem. Our problem is met in different fields, including latent structural learning and neuro-symbolic integration. Despite the existence of many learning techniques, limited theoretical analysis has been dedicated to this problem. In this paper, we provide the first theoretical study of multi-instance PLL with possibly an unknown transition $\sigma$. Our main contributions are as follows: First, we proposed a necessary and sufficient condition for the learnability of the problem. This condition nontrivially generalizes and relaxes the existing *small ambiguity degree* in PLL literature since we allow the transition to be deterministic. Second, we derived Rademacher-style error bounds based on the top-$k$ surrogate loss that is widely used in the neuro-symbolic literature. Furthermore, we conclude with empirical experiments for learning with an unknown transition. The empirical results align with our theoretical findings; however, they also expose the issue of scalability in the weak supervision literature.

Theory/Learning Theory

Trung Dang, Jasper Lee, Maoyuan 'Raymond' Song, Paul Valiant

There is growing interest in improving our algorithmic understanding of fundamental statistical problems such as mean estimation, driven by the goal of understanding the fundamental limits of what we can extract from limited and valuable data.The state of the art results for mean estimation in $\mathbb{R}$ are 1) the optimal sub-Gaussian mean estimator by [Lee and Valiant, 2022], attaining the optimal sub-Gaussian error constant for all distributions with finite but unknown variance, and 2) the analysis of the median-of-means algorithm by [Bubeck, Cesa-Bianchi and Lugosi, 2013] and a matching lower bound by [Devroye, Lerasle, Lugosi, and Oliveira, 2016], characterizing the big-O optimal errors for distributions that have tails heavy enough that only a $1+\alpha$ moment exists for some $\alpha \in (0,1)$.Both of these results, however, are optimal only in the worst case.Motivated by the recent effort in the community to go "beyond the worst-case analysis" of algorithms, we initiate the fine-grained study of the mean estimation problem:Is it possible for algorithms to leverage *beneficial* features/quirks of their input distribution to *beat* the sub-Gaussian rate, without explicit knowledge of these features?We resolve this question, finding an unexpectedly nuanced answer: "Yes in limited regimes, but in general no".Given a distribution $p$, assuming *only* that it has a finite mean and absent any additional assumptions,we show how to construct a distribution $q_{n,\delta}$ such that the means of $p$ and $q$ are well-separated, yet $p$ and $q$ are impossible to distinguish with $n$ samples with probability $1-\delta$, and $q$ further preserves the finiteness of moments of $p$.Moreover, the variance of $q$ is at most twice the variance of $p$ if it exists.The main consequence of our result is that, no reasonable estimator can asymptotically achieve better than the sub-Gaussian error rate for any distribution, up to constant factors, which matches the worst-case result of [Lee and Valiant, 2022].More generally, we introduce a new definitional framework to analyze the fine-grained optimality of algorithms, which we call "neighborhood optimality", interpolating between the unattainably strong "instance optimality" and the trivially weak admissibility/Pareto optimality definitions.As an application of the new framework, we show that the median-of-means algorithm is neighborhood optimal, up to constant factors.It is an open question to find a neighborhood-optimal estimator *without* constant factor slackness.

Theory/Learning Theory

Ingvar Ziemann, Stephen Tu, George J. Pappas, Nikolai Matni

We derive upper bounds for random design linear regression with dependent ($\beta$-mixing) data absent any realizability assumptions. In contrast to the strictly realizable martingale noise regime, no sharp \emph{instance-optimal} non-asymptotics are available in the literature. Up to constant factors, our analysis correctly recovers the variance term predicted by the Central Limit Theorem---the noise level of the problem---and thus exhibits graceful degradation as we introduce misspecification. Past a burn-in, our result is sharp in the moderate deviations regime, and in particular does not inflate the leading order term by mixing time factors.

Theory/Learning Theory

Amit Daniely, Nati Srebro, Gal Vardi

We present a PTAS for learning random constant-depth networks. We show that for any fixed $\epsilon>0$ and depth $i$, there is a poly-time algorithm that for any distribution on $\sqrt{d} \cdot \mathbb{S}^{d-1}$ learns random Xavier networks of depth $i$, up to an additive error of $\epsilon$. The algorithm runs in time and sample complexity of $(\bar{d})^{\mathrm{poly}(\epsilon^{-1})}$, where $\bar d$ is the size of the network. For some cases of sigmoid and ReLU-like activations the bound can be improved to $(\bar{d})^{\mathrm{polylog}(\epsilon^{-1})}$, resulting in a quasi-poly-time algorithm for learning constant depth random networks.

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

Mircea Petrache, Shubhendu Trivedi

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have demonstrated impressive performance across various domains and applications such as protein and drug design. A prevalent intuition about such models is that the integration of relevant symmetry results in enhanced generalization. Moreover, it is posited that when the data and/or the model exhibits only approximate or partial symmetry, the optimal or best-performing model is one where the model symmetry aligns with the data symmetry. In this paper, we conduct a formal unified investigation of these intuitions. To begin, we present quantitative bounds that demonstrate how models capturing task-specific symmetries lead to improved generalization. Utilizing this quantification, we examine the more general question of dealing with approximate/partial symmetries. We establish, for a given symmetry group, a quantitative comparison between the approximate equivariance of the model and that of the data distribution, precisely connecting model equivariance error and data equivariance error. Our result delineates the conditions under which the model equivariance error is optimal, thereby yielding the best-performing model for the given task and data.

Theory/Learning Theory

Alireza F. Pour, Hassan Ashtiani

We consider the class of noisy multi-layered sigmoid recurrent neural networks with $w$ (unbounded) weights for classification of sequences of length $T$, where independent noise distributed according to $\mathcal{N}(0,\sigma^2)$ is added to the output of each neuron in the network. Our main result shows that the sample complexity of PAC learning this class can be bounded by $O (w\log(T/\sigma))$. For the non-noisy version of the same class (i.e., $\sigma=0$), we prove a lower bound of $\Omega (wT)$ for the sample complexity. Our results indicate an exponential gap in the dependence of sample complexity on $T$ for noisy versus non-noisy networks. Moreover, given the mild logarithmic dependence of the upper bound on $1/\sigma$, this gap still holds even for numerically negligible values of $\sigma$.

Theory/Learning Theory

Tosca Lechner, Vinayak Pathak, Ruth Urner

In many real-world settings exact perturbation sets to be used by an adversary are not plausibly available to a learner. While prior literature has studied both scenarios with completely known and completely unknown perturbation sets, we propose an in-between setting of learning with respect to a class of perturbation sets. We show that in this setting we can improve on previous results with completely unknown perturbation sets, while still addressing the concerns of not having perfect knowledge of these sets in real life. In particular, we give the first positive results for the learnability of infinite Littlestone classes when having access to a perfect-attack oracle. We also consider a setting of learning with abstention, where predictions are considered robustness violations, only when the wrong prediction is made within the perturbation set. We show there are classes for which perturbation-set unaware learning without query access is possible, but abstention is required.

Theory/Learning Theory

Yilan Chen, Wei Huang, Hao Wang, Charlotte Loh, Akash Srivastava, Lam Nguyen, Lily Weng

Deep neural networks have been increasingly used in real-world applications, making it critical to ensure their ability to adapt to new, unseen data. In this paper, we study the generalization capability of neural networks trained with (stochastic) gradient flow. We establish a new connection between the loss dynamics of gradient flow and general kernel machines by proposing a new kernel, called loss path kernel. This kernel measures the similarity between two data points by evaluating the agreement between loss gradients along the path determined by the gradient flow. Based on this connection, we derive a new generalization upper bound that applies to general neural network architectures. This new bound is tight and strongly correlated with the true generalization error. We apply our results to guide the design of neural architecture search (NAS) and demonstrate favorable performance compared with state-of-the-art NAS algorithms through numerical experiments.

Theory/Learning Theory

Dario Paccagnan, Marco Campi, Simone Garatti

Generalization bounds are valuable both for theory and applications. On the one hand, they shed light on the mechanisms that underpin the learning processes; on the other, they certify how well a learned model performs against unseen inputs. In this work we build upon a recent breakthrough in compression theory to develop a new framework yielding tight generalization bounds of wide practical applicability. The core idea is to embed any given learning algorithm into a suitably-constructed meta-algorithm (here called Pick-to-Learn, P2L) in order to instill desirable compression properties. When applied to the MNIST classification dataset and to a synthetic regression problem, P2L not only attains generalization bounds that compare favorably with the state of the art (test-set and PAC-Bayes bounds), but it also learns models with better post-training performance.

Theory/Learning Theory

Xinyuan Cao, Santosh Vempala

We give a polynomial-time algorithm for learning high-dimensional halfspaces with margins in $d$-dimensional space to within desired Total Variation (TV) distance when the ambient distribution is an unknown affine transformation of the $d$-fold product of an (unknown) symmetric one-dimensional logconcave distribution, and the halfspace is introduced by deleting at least an $\epsilon$ fraction of the data in one of the component distributions. Notably, our algorithm does not need labels and establishes the unique (and efficient) identifiability of the hidden halfspace under this distributional assumption. The sample and time complexity of the algorithm are polynomial in the dimension and $1/\epsilon$. The algorithm uses only the first two moments of *suitable re-weightings* of the empirical distribution, which we call *contrastive moments*; its analysis uses classical facts about generalized Dirichlet polynomials and relies crucially on a new monotonicity property of the moment ratio of truncations of logconcave distributions. Such algorithms, based only on first and second moments were suggested in earlier work, but hitherto eluded rigorous guarantees.Prior work addressed the special case when the underlying distribution is Gaussian via Non-Gaussian Component Analysis. We improve on this by providing polytime guarantees based on TV distance, in place of existing moment-bound guarantees that can be super-polynomial. Our work is also the first to go beyond Gaussians in this setting.

Theory/Learning Theory

Ilias Diakonikolas, Daniel Kane, Ankit Pensia, Thanasis Pittas

We study the fundamental problems of Gaussian mean estimation and linear regression with Gaussian covariates in the presence of Huber contamination. Our main contribution is the design of the first sample near-optimal and almost linear-time algorithms with optimal error guarantees for both these problems. Specifically, for Gaussian robust mean estimation on $\mathbb R^d$ with contamination parameter $\epsilon \in (0, \epsilon_0)$ for a small absolute constant $\epsilon_0$, we give an algorithm with sample complexity $n = \tilde{O}(d/\epsilon^2)$ and almost linear runtime that approximates the target mean within $\ell_2$-error $O(\epsilon)$. This improves on prior work that achieved this error guarantee with polynomially suboptimal sample and time complexity. For robust linear regression, we give the first algorithm with sample complexity $n = \tilde{O}(d/\epsilon^2)$ and almost linear runtime that approximates the target regressor within $\ell_2$-error $O(\epsilon)$. This is the first polynomial sample and time algorithm achieving the optimal error guarantee, answering an open question in the literature. At the technical level, we develop a methodology that yields almost-linear time algorithms for multi-directional filtering that may be of broader interest.

Theory/Learning Theory

Jose Blanchet, Haoxuan Chen, Yiping Lu, Lexing Ying

This paper studies the use of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, we seek to uncover the key factors that influence the efficiency of control variates in reducing variance. We examine a prototype estimation problem that involves simulating the moments of a Sobolev function based on observations obtained from (random) quadrature nodes. Firstly, we establish an information-theoretic lower bound for the problem. We then study a specific quadrature rule that employs a nonparametric regression-adjusted control variate to reduce the variance of the Monte Carlo simulation. We demonstrate that this kind of quadrature rule can improve the Monte Carlo rate and achieve the minimax optimal rate under a sufficient smoothness assumption. Due to the Sobolev Embedding Theorem, the sufficient smoothness assumption eliminates the existence of rare and extreme events. Finally, we show that, in the presence of rare and extreme events, a truncated version of the Monte Carlo algorithm can achieve the minimax optimal rate while the control variate cannot improve the convergence rate.

Theory/Learning Theory

Ilias Diakonikolas, Daniel Kane, Jasper Lee, Ankit Pensia, Thanasis Pittas

We study the problem of list-decodable Gaussian covariance estimation. Given a multiset $T$ of $n$ points in $\mathbb{R}^d$ such that an unknown $\alpha<1/2$ fraction of points in $T$ are i.i.d. samples from an unknown Gaussian $\mathcal{N}(\mu, \Sigma)$, the goal is to output a list of $O(1/\alpha)$ hypotheses at least one of which is close to $\Sigma$ in relative Frobenius norm. Our main result is a $\mathrm{poly}(d,1/\alpha)$ sample and time algorithm for this task that guarantees relative Frobenius norm error of $\mathrm{poly}(1/\alpha)$. Importantly, our algorithm relies purely on spectral techniques. As a corollary, we obtain an efficient spectral algorithm for robust partial clustering of Gaussian mixture models (GMMs) --- a key ingredient in the recent work of [BakDJKKV22] on robustly learning arbitrary GMMs. Combined with the other components of [BakDJKKV22], our new method yields the first Sum-of-Squares-free algorithm for robustly learning GMMs, resolving an open problem proposed by Vempala and Kothari. At the technical level, we develop a novel multi-filtering method for list-decodable covariance estimation that may be useful in other settings.

Theory/Learning Theory

Jingwen Fu, Zhizheng Zhang, Dacheng Yin, Yan Lu, Nanning Zheng

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the generalization error of the DNN post-training, we present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error. This perspective enable a more direct comprehension of how the learning trajectory influences generalization error. Building upon this analysis, we propose a new generalization bound that incorporates more extensive trajectory information.Our proposed generalization bound depends on the complexity of learning trajectory and the ratio between the bias and diversity of training set. Experimental observations reveal that our method effectively captures the generalization error throughout the training process. Furthermore, our approach can also track changes in generalization error when adjustments are made to learning rates and label noise levels. These results demonstrate that learning trajectory information is a valuable indicator of a model's generalization capabilities.

Theory/Learning Theory

Sijia Zhou, Yunwen Lei, Ata Kaban

We give sharper bounds for uniformly stable randomized algorithms in a PAC-Bayesian framework, which improve the existing results by up to a factor of $\sqrt{n}$ (ignoring a log factor), where $n$ is the sample size. The key idea is to bound the moment generating function of the generalization gap using concentration of weakly dependent random variables due to Bousquet et al (2020). We introduce an assumption of sub-exponential stability parameter, which allows a general treatment that we instantiate in two applications: stochastic gradient descent and randomized coordinate descent. Our results eliminate the requirement of strong convexity from previous results, and hold for non-smooth convex problems.

Theory/Learning Theory

Kazuto Fukuchi, Jun Sakuma

We explore the minimax optimal error associated with a demographic parity-constrained regression problem within the context of a linear model. Our proposed model encompasses a broader range of discriminatory bias sources compared to the model presented by Chzhen and Schreuder. Our analysis reveals that the minimax optimal error for the demographic parity-constrained regression problem under our model is characterized by $\Theta(\frac{dM}{n})$, where $n$ denotes the sample size, $d$ represents the dimensionality, and $M$ signifies the number of demographic groups arising from sensitive attributes. Moreover, we demonstrate that the minimax error increases in conjunction with a larger bias present in the model.

Theory/Learning Theory

Vivien Cabannes, Stefano Vigogna

A core principle in statistical learning is that smoothness of target functions allows to break the curse of dimensionality. However, learning a smooth function seems to require enough samples close to one another to get meaningful estimate of high-order derivatives, which would be hard in machine learning problems where the ratio between number of data and input dimension is relatively small. By deriving new lower bounds on the generalization error, this paper formalizes such an intuition, before investigating the role of constants and transitory regimes which are usually not depicted beyond classical learning theory statements while they play a dominant role in practice.

Theory/Learning Theory

Roey Magen, Ohad Shamir

We provide several new results on the sample complexity of vector-valued linear predictors (parameterized by a matrix), and more generally neural networks. Focusing on size-independent bounds, where only the Frobenius norm distance of the parameters from some fixed reference matrix $W_0$ is controlled, we show that the sample complexity behavior can be surprisingly different than what we may expect considering the well-studied setting of scalar-valued linear predictors. This also leads to new sample complexity bounds for feed-forward neural networks, tackling some open questions in the literature, and establishing a new convex linear prediction problem that is provably learnable without uniform convergence.