In recent years, there has been a significant transformation in medical research methodologies towards the adoption of Deep Learning (DL) techniques for predicting critical events, such as disease development and patient mortality. Despite their potential to handle complex data, practical applications in this domain remain limited, with most studies still relying on traditional statistical methods. Survival Analysis (SA), or time-to-event analysis, is an essential tool for studying specific events in various disciplines, not only in medicine but also in fields such as recommendation systems [1], employee retention [2], market modeling [3], and financial risk assessment [4]. According to the existing literature, the Cox proportional hazards model (Cox-PH) [5] is the dominant SA method that offers a semiparametric regression solution to the non-parametric Kaplan-Meier estimator problem [6]. Unlike the Kaplan-Meier method, which uses a single covariate, Cox-PH incorporates multiple covariates to predict event times and assess their impact on the hazard rate at specific time points. However, it is crucial to acknowledge that the Cox-PH model is built on certain strong assumptions. One of these is the proportional hazards assumption, which posits that different individuals have hazard functions that remain constant over time. Furthermore, the model assumes a linear relation between the natural logarithm of the relative hazard (the ratio of the hazard at time t to the baseline hazard) and the covariates. Furthermore, it assumes the absence of interactions among these covariates.

The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-reversal argument to construct a diffusion process targeting the desired data distribution. We show that the time-reversal argument, common to all denoising diffusion probabilistic modeling proposals, is not necessary. We obtain diffusion processes targeting the desired data distribution by taking appropriate mixtures of diffusion bridges. The resulting transport is exact by construction, allows for greater flexibility in choosing the dynamics of the underlying diffusion, and can be approximated by means of a neural network via novel training objectives. We develop a unifying view of the drift adjustments corresponding to our and to time-reversal approaches and make use of this representation to inspect the inner workings of diffusion-based generative models. Finally, we leverage on scalable simulation and inference techniques common in spatial statistics to move beyond fully factorial distributions in the underlying diffusion dynamics. The methodological advances contained in this work contribute toward establishing a general framework for generative modeling based on diffusion processes.

The dynamic Schr\"odinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being closest, in terms of Kullback-Leibler divergence, to a reference process. We propose a novel sampling-based iterative algorithm, the iterated diffusion bridge mixture (IDBM) procedure, aimed at solving the dynamic Schr\"odinger bridge problem. The IDBM procedure exhibits the attractive property of realizing a valid transport between the target probability measures at each iteration. We perform an initial theoretical investigation of the IDBM procedure, establishing its convergence properties. The theoretical findings are complemented by numerical experiments illustrating the competitive performance of the IDBM procedure. Recent advancements in generative modeling employ the time-reversal of a diffusion process to define a generative process that approximately transports a simple distribution to the data distribution. As an alternative, we propose utilizing the first iteration of the IDBM procedure as an approximation-free method for realizing this transport. This approach offers greater flexibility in selecting the generative process dynamics and exhibits accelerated training and superior sample quality over larger discretization intervals. In terms of implementation, the necessary modifications are minimally intrusive, being limited to the training loss definition.

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of related tasks available is often small, most of the existing approaches assume an abundance of tasks; making them unrealistic and prone to overfitting. A central question in the meta-learning literature is how to regularize to ensure generalization to unseen tasks. In this work, we provide a theoretical analysis using the PAC-Bayesian theory and present a generalization bound for meta-learning, which was first derived by Rothfuss et al. (2021a). Crucially, the bound allows us to derive the closed form of the optimal hyper-posterior, referred to as PACOH, which leads to the best performance guarantees. We provide a theoretical analysis and empirical case study under which conditions and to what extent these guarantees for meta-learning improve upon PAC-Bayesian per-task learning bounds. The closed-form PACOH inspires a practical meta-learning approach that avoids the reliance on bi-level optimization, giving rise to a stochastic optimization problem that is amenable to standard variational methods that scale well. Our experiments show that, when instantiating the PACOH with Gaussian processes and Bayesian Neural Networks models, the resulting methods are more scalable, and yield state-of-the-art performance, both in terms of predictive accuracy and the quality of uncertainty estimates.

We consider the problem of finding the smallest or largest entry of a tensor of order N that is specified via its rank decomposition. Stated in a different way, we are given N sets of R-dimensional vectors and we wish to select one vector from each set such that the sum of the Hadamard product of the selected vectors is minimized or maximized. We show that this fundamental tensor problem is NP-hard for any tensor rank higher than one, and polynomial-time solvable in the rank-one case. We also propose a continuous relaxation and prove that it is tight for any rank. For low-enough ranks, the proposed continuous reformulation is amenable to low-complexity gradient-based optimization, and we propose a suite of gradient-based optimization algorithms drawing from projected gradient descent, Frank-Wolfe, or explicit parametrization of the relaxed constraints. We also show that our core results remain valid no matter what kind of polyadic tensor model is used to represent the tensor of interest, including Tucker, HOSVD/MLSVD, tensor train, or tensor ring. Next, we consider the class of problems that can be posed as special instances of the problem of interest. We show that this class includes the partition problem (and thus all NP-complete problems via polynomial-time transformation), integer least squares, integer linear programming, integer quadratic programming, sign retrieval (a special kind of mixed integer programming / restricted version of phase retrieval), and maximum likelihood decoding of parity check codes. We demonstrate promising experimental results on a number of hard problems, including state-of-art performance in decoding low density parity check codes and general parity check codes.

Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the exploration-exploitation dilemma. Nonetheless, a majority of these techniques only invoke the inference-control duality to derive a modified risk objective that is then addressed within a reinforcement learning framework. This paper introduces a novel perspective by framing risk-sensitive stochastic control as Markovian score climbing under samples drawn from a conditional particle filter. Our approach, while purely inference-centric, provides asymptotically unbiased estimates for gradient-based policy optimization with optimal importance weighting and no explicit value function learning. To validate our methodology, we apply it to the task of learning neural non-Gaussian feedback policies, showcasing its efficacy on numerical benchmarks of stochastic dynamical systems.

We obtain asymptotically sharp error estimates for the consistency error of the Target Measure Diffusion map (TMDmap) (Banisch et al. 2020), a variant of diffusion maps featuring importance sampling and hence allowing input data drawn from an arbitrary density. The derived error estimates include the bias error and the variance error. The resulting convergence rates are consistent with the approximation theory of graph Laplacians. The key novelty of our results lies in the explicit quantification of all the prefactors on leading-order terms. We also prove an error estimate for solutions of Dirichlet BVPs obtained using TMDmap, showing that the solution error is controlled by consistency error. We use these results to study an important application of TMDmap in the analysis of rare events in systems governed by overdamped Langevin dynamics using the framework of transition path theory (TPT). The cornerstone ingredient of TPT is the solution of the committor problem, a boundary value problem for the backward Kolmogorov PDE. Remarkably, we find that the TMDmap algorithm is particularly suited as a meshless solver to the committor problem due to the cancellation of several error terms in the prefactor formula. Furthermore, significant improvements in bias and variance errors occur when using a quasi-uniform sampling density. Our numerical experiments show that these improvements in accuracy are realizable in practice when using $\delta$-nets as spatially uniform inputs to the TMDmap algorithm.

Typical investors start off the day by going through the daily news to get an intuition about the performance of the market. The speculations based on the tone of the news ultimately shape their responses towards the market. Today, computers are being trained to compute the news sentiment so that it can be used as a variable to predict stock market movements and returns. Some researchers have even developed news-based market indices to forecast stock market returns. Majority of the research in the field of news sentiment analysis has focussed on using libraries like Vader, Loughran-McDonald (LM), Harvard IV and Pattern. However, are the popular approaches for measuring financial news sentiment really approaching the problem of sentiment analysis correctly? Our experiments suggest that measuring sentiments using these libraries, especially for financial news, fails to depict the true picture and hence may not be very reliable. Therefore, the question remains: What is the most effective and accurate approach to measure financial news sentiment? Our paper explores these questions and attempts to answer them through SENTInews: a one-of-its-kind financial news sentiment analyzer customized to the Indian context

Generative Flow Networks (GFNs) have emerged as a powerful tool for sampling discrete objects from unnormalized distributions, offering a scalable alternative to Markov Chain Monte Carlo (MCMC) methods. While GFNs draw inspiration from maximum entropy reinforcement learning (RL), the connection between the two has largely been unclear and seemingly applicable only in specific cases. This paper addresses the connection by constructing an appropriate reward function, thereby establishing an exact relationship between GFNs and maximum entropy RL. This construction allows us to introduce maximum entropy GFNs, which, in contrast to GFNs with uniform backward policy, achieve the maximum entropy attainable by GFNs without constraints on the state space.

Significant research effort has been devoted in recent years to developing personalized pricing, promotions, and product recommendation algorithms that can leverage rich customer data to learn and earn. Systematic benchmarking and evaluation of these causal learning systems remains a critical challenge, due to the lack of suitable datasets and simulation environments. In this work, we propose a multi-stage model for simulating customer shopping behavior that captures important sources of heterogeneity, including price sensitivity and past experiences. We embedded this model into a working simulation environment -- RetailSynth. RetailSynth was carefully calibrated on publicly available grocery data to create realistic synthetic shopping transactions. Multiple pricing policies were implemented within the simulator and analyzed for impact on revenue, category penetration, and customer retention. Applied researchers can use RetailSynth to validate causal demand models for multi-category retail and to incorporate realistic price sensitivity into emerging benchmarking suites for personalized pricing, promotions, and product recommendations.