This paper jointly addresses the problem of data uncertainty, popularity bias, and exposure bias in session-based recommender systems. We study the symptoms of this bias both in item embeddings and in recommendations. We propose treating user interest as a stochastic process in the latent space and providing a model-agnostic implementation of this mathematical concept. The proposed stochastic component consists of elements: debiasing item embeddings with regularization for embedding uniformity, modeling dense user interest from session prefixes, and introducing fake targets in the data to simulate extended exposure. We conducted computational experiments on two popular benchmark datasets, Diginetica and YooChoose 1/64, as well as several modifications of the YooChoose dataset with different ratios of popular items. The results show that the proposed approach allows us to mitigate the challenges mentioned.

We study the problem of learning binary classifiers from positive and unlabeled data when the unlabeled data distribution is shifted, which we call Positive and Imperfect Unlabeled (PIU) Learning. In the absence of covariate shifts, i.e., with perfect unlabeled data, Denis (1998) reduced this problem to learning under Massart noise; however, that reduction fails under even slight shifts. Our main results on PIU learning are the characterizations of the sample complexity of PIU learning and a computationally and sample-efficient algorithm achieving a misclassification error $\varepsilon$. We further show that our results lead to new algorithms for several related problems. 1. Learning from smooth distributions: We give algorithms that learn interesting concept classes from only positive samples under smooth feature distributions, bypassing known existing impossibility results and contributing to recent advances in smoothened learning (Haghtalab et al, J.ACM'24) (Chandrasekaran et al., COLT'24). 2. Learning with a list of unlabeled distributions: We design new algorithms that apply to a broad class of concept classes under the assumption that we are given a list of unlabeled distributions, one of which--unknown to the learner--is $O(1)$-close to the true feature distribution. 3. Estimation in the presence of unknown truncation: We give the first polynomial sample and time algorithm for estimating the parameters of an exponential family distribution from samples truncated to an unknown set approximable by polynomials in $L_1$-norm. This improves the algorithm by Lee et al. (FOCS'24) that requires approximation in $L_2$-norm. 4. Detecting truncation: We present new algorithms for detecting whether given samples have been truncated (or not) for a broad class of non-product distributions, including non-product distributions, improving the algorithm by De et al. (STOC'24).

We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ``interpretability'' or ``suitability for safety-critical applications'' of such models.

Low-rank Matrix Completion (LRMC) describes the problem where we wish to recover missing entries of partially observed low-rank matrix. Most existing matrix completion work deals with sampling procedures that are independent of the underlying data values. While this assumption allows the derivation of nice theoretical guarantees, it seldom holds in real-world applications. In this paper, we consider various settings where the sampling mask is dependent on the underlying data values, motivated by applications in sensing, sequential decision-making, and recommender systems. Through a series of experiments, we study and compare the performance of various LRMC algorithms that were originally successful for data-independent sampling patterns.

Aggregation methods have emerged as a powerful and flexible framework in statistical learning, providing unified solutions across diverse problems such as regression, classification, and density estimation. In the context of generalized linear models (GLMs), where responses follow exponential family distributions, aggregation offers an attractive alternative to classical parametric modeling. This paper investigates the problem of sparse aggregation in GLMs, aiming to approximate the true parameter vector by a sparse linear combination of predictors. We prove that an exponential weighted aggregation scheme yields a sharp oracle inequality for the Kullback-Leibler risk with leading constant equal to one, while also attaining the minimax-optimal rate of aggregation. These results are further enhanced by establishing high-probability bounds on the excess risk.

Equations, particularly differential equations, are fundamental for understanding natural phenomena and predicting complex dynamics across various scientific and engineering disciplines. However, the governing equations for many complex systems remain unknown due to intricate underlying mechanisms. Recent advancements in machine learning and data science offer a new paradigm for modeling unknown equations from measurement or simulation data. This paradigm shift, known as data-driven discovery or modeling, stands at the forefront of AI for science, with significant progress made in recent years. In this paper, we introduce a systematic framework for data-driven modeling of unknown equations using deep learning. This versatile framework is capable of learning unknown ODEs, PDEs, DAEs, IDEs, SDEs, reduced or partially observed systems, and non-autonomous differential equations. Based on this framework, we have developed Deep Unknown Equations (DUE), an open-source software package designed to facilitate the data-driven modeling of unknown equations using modern deep learning techniques. DUE serves as an educational tool for classroom instruction, enabling students and newcomers to gain hands-on experience with differential equations, data-driven modeling, and contemporary deep learning approaches such as FNN, ResNet, generalized ResNet, operator semigroup networks (OSG-Net), and Transformers. Additionally, DUE is a versatile and accessible toolkit for researchers across various scientific and engineering fields. It is applicable not only for learning unknown equations from data but also for surrogate modeling of known, yet complex, equations that are costly to solve using traditional numerical methods. We provide detailed descriptions of DUE and demonstrate its capabilities through diverse examples, which serve as templates that can be easily adapted for other applications.

Recent efforts have extended the flow-matching framework to discrete generative modeling. One strand of models directly works with the continuous probabilities instead of discrete tokens, which we colloquially refer to as Continuous-State Discrete Flow Matching (CS-DFM). Existing CS-DFM models differ significantly in their representations and geometric assumptions. This work presents a unified framework for CS-DFM models, under which the existing variants can be understood as operating on different $\alpha$-representations of probabilities. Building upon the theory of information geometry, we introduce $\alpha$-Flow, a family of CS-DFM models that adheres to the canonical $\alpha$-geometry of the statistical manifold, and demonstrate its optimality in minimizing the generalized kinetic energy. Theoretically, we show that the flow matching loss for $\alpha$-flow establishes a unified variational bound for the discrete negative log-likelihood. We comprehensively evaluate different instantiations of $\alpha$-flow on various discrete generation domains to demonstrate their effectiveness in discrete generative modeling, including intermediate values whose geometries have never been explored before. $\alpha$-flow significantly outperforms its discrete-state counterpart in image and protein sequence generation and better captures the entropy in language modeling.

Existing distribution compression methods, like Kernel Herding (KH), were originally developed for unlabelled data. However, no existing approach directly compresses the conditional distribution of labelled data. To address this gap, we first introduce the Average Maximum Conditional Mean Discrepancy (AMCMD), a natural metric for comparing conditional distributions. We then derive a consistent estimator for the AMCMD and establish its rate of convergence. Next, we make a key observation: in the context of distribution compression, the cost of constructing a compressed set targeting the AMCMD can be reduced from $\mathcal{O}(n^3)$ to $\mathcal{O}(n)$. Building on this, we extend the idea of KH to develop Average Conditional Kernel Herding (ACKH), a linear-time greedy algorithm that constructs a compressed set targeting the AMCMD. To better understand the advantages of directly compressing the conditional distribution rather than doing so via the joint distribution, we introduce Joint Kernel Herding (JKH), a straightforward adaptation of KH designed to compress the joint distribution of labelled data. While herding methods provide a simple and interpretable selection process, they rely on a greedy heuristic. To explore alternative optimisation strategies, we propose Joint Kernel Inducing Points (JKIP) and Average Conditional Kernel Inducing Points (ACKIP), which jointly optimise the compressed set while maintaining linear complexity. Experiments show that directly preserving conditional distributions with ACKIP outperforms both joint distribution compression (via JKH and JKIP) and the greedy selection used in ACKH. Moreover, we see that JKIP consistently outperforms JKH.

We revisit a classical assumption for analyzing stochastic gradient algorithms where the squared norm of the stochastic subgradient (or the variance for smooth problems) is allowed to grow as fast as the squared norm of the optimization variable. We contextualize this assumption in view of its inception in the 1960s, its seemingly independent appearance in the recent literature, its relationship to weakest-known variance assumptions for analyzing stochastic gradient algorithms, and its relevance in deterministic problems for non-Lipschitz nonsmooth convex optimization. We build on and extend a connection recently made between this assumption and the Halpern iteration. For convex nonsmooth, and potentially stochastic, optimization, we analyze horizon-free, anytime algorithms with last-iterate rates. For problems beyond simple constrained optimization, such as convex problems with functional constraints or regularized convex-concave min-max problems, we obtain rates for optimality measures that do not require boundedness of the feasible set.

With just one click, the AI technology begins transcribing the doctor's conversation with a patient. DENVER – Artificial intelligence is quietly transforming how doctors interact with patients -- and it might already be in use during your next visit to the doctor's office. Thousands of physicians across the country are using a form of AI called ambient listening, surveys show. This technology listens to conversations between doctors and patients, creates real-time transcriptions, and then compiles detailed clinical notes -- all without disrupting the flow of the appointment. Dr. Daniel Kortsch, associate chief of artificial intelligence and digital health at Denver Health, said that ambient listening technology has made a big difference since his practice began using it in fall 2024.