We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning. To address the challenge of computing the integral in the partition function for each anchor data, we leverage the multiple importance sampling (MIS) technique for robust Monte Carlo integration, which can recover InfoNCE-based contrastive loss as a special case. Within this probabilistic modeling framework, we conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning and derive insights for developing better approaches by reducing the error of Monte Carlo integration. To this end, we propose a novel non-parametric method for approximating the sum of conditional densities required by MIS through convex optimization, yielding a new contrastive objective for self-supervised representation learning. Moreover, we design an efficient algorithm for solving the proposed objective. We empirically compare our algorithm to representative baselines on the contrastive image-language pretraining task. Experimental results on the CC3M and CC12M datasets demonstrate the superior overall performance of our algorithm.

Neural scaling laws describe how the performance of deep neural networks scales with key factors such as training data size, model complexity, and training time, often following power-law behaviors over multiple orders of magnitude. Despite their empirical observation, the theoretical understanding of these scaling laws remains limited. In this work, we employ techniques from statistical mechanics to analyze one-pass stochastic gradient descent within a student-teacher framework, where both the student and teacher are two-layer neural networks. Our study primarily focuses on the generalization error and its behavior in response to data covariance matrices that exhibit power-law spectra. For linear activation functions, we derive analytical expressions for the generalization error, exploring different learning regimes and identifying conditions under which power-law scaling emerges. Additionally, we extend our analysis to non-linear activation functions in the feature learning regime, investigating how power-law spectra in the data covariance matrix impact learning dynamics. Importantly, we find that the length of the symmetric plateau depends on the number of distinct eigenvalues of the data covariance matrix and the number of hidden units, demonstrating how these plateaus behave under various configurations. In addition, our results reveal a transition from exponential to power-law convergence in the specialized phase when the data covariance matrix possesses a power-law spectrum. This work contributes to the theoretical understanding of neural scaling laws and provides insights into optimizing learning performance in practical scenarios involving complex data structures.

Downsampling or under-sampling is a technique that is utilized in the context of large and highly imbalanced classification models. We study optimal downsampling for imbalanced classification using generalized linear models (GLMs). We propose a pseudo maximum likelihood estimator and study its asymptotic normality in the context of increasingly imbalanced populations relative to an increasingly large sample size. We provide theoretical guarantees for the introduced estimator. Additionally, we compute the optimal downsampling rate using a criterion that balances statistical accuracy and computational efficiency. Our numerical experiments, conducted on both synthetic and empirical data, further validate our theoretical results, and demonstrate that the introduced estimator outperforms commonly available alternatives.

Traditional generalization results in statistical learning require a training data set made of independently drawn examples. Most of the recent efforts to relax this independence assumption have considered either purely temporal (mixing) dependencies, or graph-dependencies, where non-adjacent vertices correspond to independent random variables. Both approaches have their own limitations, the former requiring a temporal ordered structure, and the latter lacking a way to quantify the strength of inter-dependencies. In this work, we bridge these two lines of work by proposing a framework where dependencies decay with graph distance. We derive generalization bounds leveraging the online-to-PAC framework, by deriving a concentration result and introducing an online learning framework incorporating the graph structure. The resulting high-probability generalization guarantees depend on both the mixing rate and the graph's chromatic number.

A common objective in statistical learning is uncertainty quantification. This task is well-studied and forms a key component of supervised and unsupervised statistical learning. In the context of regression this amounts to estimating the generalisation error, i.e., the expected mean-squared prediction error (MSPE) for unknown test observations. Usually either analytic methods for a specific model, or computational algorithms, e.g., the bootstrap or cross-validation, are employed for obtaining generalisation error estimates; see, e.g., Stone (1974), Efron & Tibshirani (1994), Chapter 7 in Hastie et al. (2017), Hastie et al. (2015), Nadeau & Bengio (1999), Wainwright (2019), Wasserman (2010). Moreover, these generalisation error estimates can be used for comparing different models, cross-validation during training, and selecting a final model from a finite collection of candidate models; see, e.g., Wood (2017), David J. Olive & Haile (2022), Das & Nason (2016).

In recent years, unbiased Markov Chain Monte Carlo via couplings (UMCMC) has emerged as a promising framework to remove bias from MCMC estimates, thus potentially allowing for early stopping, simplifying the convergence diagnostic process and facilitating parallelization (Glynn and Rhee, 2014; Jacob et al., 2020). In UMCMC, coupled chains are run for a random number of iterations (at least up to coalescence) and their values are combined to produce unbiased estimates. A natural question that arises is whether this class of estimates incurs a greater computational cost than conventional MCMC based on simple ergodic averages and to quantify this potential difference. Framing the question differently, one may ask whether it is possible to devise UMCMC methods with computational cost matching top performing MCMCs, while enjoying the above mentioned benefits. On a different line of research, various works showed how carefully designed blocked Gibbs Samplers (BGSs), i.e. Gibbs sampling schemes that update entire blocks of coordinates jointly, can achieve state-of-the-art performances for sampling from the posterior distributions of various challenging high-dimensional Bayesian models, such as non-nested models with crossed dependencies (Papaspiliopoulos et al., 2019, 2023). In particular, BGSs achieve linear computational costs in the number of parameters and observations in asymptotic regimes where both diverge to infinity.

In this paper, we establish the global convergence of the actor-critic algorithm with a significantly improved sample complexity of $O(\epsilon^{-3})$, advancing beyond the existing local convergence results. Previous works provide local convergence guarantees with a sample complexity of $O(\epsilon^{-2})$ for bounding the squared gradient of the return, which translates to a global sample complexity of $O(\epsilon^{-4})$ using the gradient domination lemma. In contrast to traditional methods that employ decreasing step sizes for both the actor and critic, we demonstrate that a constant step size for the critic is sufficient to ensure convergence in expectation. This key insight reveals that using a decreasing step size for the actor alone is sufficient to handle the noise for both the actor and critic. Our findings provide theoretical support for the practical success of many algorithms that rely on constant step sizes.

Bayesian optimization (BO) is an attractive machine learning framework for performing sample-efficient global optimization of black-box functions. The optimization process is guided by an acquisition function that selects points to acquire in each round of BO. In batched BO, when multiple points are acquired in parallel, commonly used acquisition functions are often high-dimensional and intractable, leading to the use of sampling-based alternatives. We propose a statistical physics inspired acquisition function for BO with Gaussian processes that can natively handle batches. Batched Energy-Entropy acquisition for BO (BEEBO) enables tight control of the explore-exploit trade-off of the optimization process and generalizes to heteroskedastic black-box problems. We demonstrate the applicability of BEEBO on a range of problems, showing competitive performance to existing methods.

Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes. Here, we present how methods from causal ML can be used to understand the effectiveness of treatments, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that allows for estimating individualized treatment effects, as well as personalized predictions of potential patient outcomes under different treatments. This offers granular insights into when treatments are effective, so that decision-making in patient care can be personalized to individual patient profiles. We further discuss how causal ML can be used in combination with both clinical trial data as well as real-world data such as clinical registries and electronic health records. We finally provide recommendations for the reliable use of causal ML in medicine. First published in Nature Medicine, 30, 958-968 (2024) by Springer Nature. Assessing the effectiveness of treatments is crucial to ensure patient safety and personalize patient care. Recent innovations in machine learning (ML) offer new, data-driven methods to estimate treatment effects from data. This branch in ML is commonly referred to as causal ML as it aims to predict a causal quantity, namely, the patient outcomes due to treatment [1]. Causal ML can be used in order to estimate treatment effects from both experimental data obtained through randomized controlled trials (RCTs) and observational data obtained from clinical registries, electronic health records, and other real-world data (RWD) sources to generate clinical evidence. A key strength of causal ML is that it allows to estimate individualized treatment effects, as well as to make personalized predictions of potential patient outcomes under different treatments.

Receiver Operating Characteristic (ROC) curves are useful for evaluation in binary classification and changepoint detection, but difficult to use for learning since the Area Under the Curve (AUC) is piecewise constant (gradient zero almost everywhere). Recently the Area Under Min (AUM) of false positive and false negative rates has been proposed as a differentiable surrogate for AUC. In this paper we study the piecewise linear/constant nature of the AUM/AUC, and propose new efficient path-following algorithms for choosing the learning rate which is optimal for each step of gradient descent (line search), when optimizing a linear model. Remarkably, our proposed line search algorithm has the same log-linear asymptotic time complexity as gradient descent with constant step size, but it computes a complete representation of the AUM/AUC as a function of step size. In our empirical study of binary classification problems, we verify that our proposed algorithm is fast and exact; in changepoint detection problems we show that the proposed algorithm is just as accurate as grid search, but faster.