To predict the next token, autoregressive models However, those NP-hard distributions are artificial. For naturally ordinarily examine the past. Could they also benefit occurring sequences, why might one expect lookahead from also examining hypothetical futures? We to help autoregressive modeling? We argue that when the consider a novel Transformer-based autoregressive sequences represent an agent's behavior, an autoregressive architecture that estimates the next-token distribution parameterization is not always the simplest description. If by extrapolating multiple continuations the behavior is goal-directed--for example, an agent trying of the past, according to some proposal distribution, to achieve high reward in a Markov Decision Process--then and attending to these extended strings. This the simplest description may include a characterization of architecture draws insights from classical AI systems the agent's environment and goals. Even if the agent explicitly such as board game players: when making consults an autoregressive policy p(action | state) a local decision, a policy may benefit from exploring at each step, that policy is not arbitrary: while it may appear possible future trajectories and analyzing complex, it was shaped by reinforcement learning or them. On multiple tasks including morphological by natural selection so as to achieve high-reward trajectories.

Polar slice sampling (Roberts & Rosenthal, 2002) is a Markov chain approach for approximate sampling of distributions that is difficult, if not impossible, to implement efficiently, but behaves provably well with respect to the dimension. By updating the directional and radial components of chain iterates separately, we obtain a family of samplers that mimic polar slice sampling, and yet can be implemented efficiently. Numerical experiments in a variety of settings indicate that our proposed algorithm outperforms the two most closely related approaches, elliptical slice sampling (Murray et al., 2010) and hit-and-run uniform slice sampling (MacKay, 2003). We prove the well-definedness and convergence of our methods under suitable assumptions on the target distribution.

Conventional Bayesian Neural Networks (BNNs) cannot leverage unlabelled data to improve their predictions. To overcome this limitation, we introduce Self-Supervised Bayesian Neural Networks, which use unlabelled data to learn improved prior predictive distributions by maximising an evidence lower bound during an unsupervised pre-training step. With a novel methodology developed to better understand prior predictive distributions, we then show that self-supervised prior predictives capture image semantics better than conventional BNN priors. In our empirical evaluations, we see that self-supervised BNNs offer the label efficiency of self-supervised methods and the uncertainty estimates of Bayesian methods, particularly outperforming conventional BNNs in low-to-medium data regimes.

The problem of reducing a Hidden Markov Model (HMM) to one of smaller dimension that exactly reproduces the same marginals is tackled by using a system-theoretic approach. Realization theory tools are extended to HMMs by leveraging suitable algebraic representations of probability spaces. We propose two algorithms that return coarse-grained equivalent HMMs obtained by stochastic projection operators: the first returns models that exactly reproduce the single-time distribution of a given output process, while in the second the full (multi-time) distribution is preserved. The reduction method exploits not only the structure of the observed output, but also its initial condition, whenever the latter is known or belongs to a given subclass. Optimal algorithms are derived for a class of HMM, namely observable ones.

Inferring a state sequence from a sequence of measurements is a fundamental problem in bioinformatics and natural language processing. The Viterbi and the Beam Search (BS) algorithms are popular inference methods, but they have limitations when applied to Hierarchical Hidden Markov Models (HHMMs), where the interest lies in the outer state sequence. The Viterbi algorithm can not infer outer states without inner states, while the BS algorithm requires marginalization over prohibitively large state spaces. We propose two new algorithms to overcome these limitations: the greedy marginalized BS algorithm and the local focus BS algorithm. We show that they approximate the most likely outer state sequence with higher performance than the Viterbi algorithm, and we evaluate the performance of these algorithms on an explicit duration HMM with simulation and nanopore base calling data.

We propose a novel method for predicting time-to-event in the presence of cure fractions based on flexible survivals models integrated into a deep neural network framework. Our approach allows for non-linear relationships and high-dimensional interactions between covariates and survival and is suitable for large-scale applications. Furthermore, we allow the method to incorporate an identified predictor formed of an additive decomposition of interpretable linear and non-linear effects and add an orthogonalization layer to capture potential higher dimensional interactions. We demonstrate the usefulness and computational efficiency of our method via simulations and apply it to a large portfolio of US mortgage loans. Here, we find not only a better predictive performance of our framework but also a more realistic picture of covariate effects.

We study the computational complexity of counterfactual reasoning in relation to the complexity of associational and interventional reasoning on structural causal models (SCMs). We show that counterfactual reasoning is no harder than associational or interventional reasoning on fully specified SCMs in the context of two computational frameworks. The first framework is based on the notion of treewidth and includes the classical variable elimination and jointree algorithms. The second framework is based on the more recent and refined notion of causal treewidth which is directed towards models with functional dependencies such as SCMs. Our results are constructive and based on bounding the (causal) treewidth of twin networks -- used in standard counterfactual reasoning that contemplates two worlds, real and imaginary -- to the (causal) treewidth of the underlying SCM structure. In particular, we show that the latter (causal) treewidth is no more than twice the former plus one. Hence, if associational or interventional reasoning is tractable on a fully specified SCM then counterfactual reasoning is tractable too. We extend our results to general counterfactual reasoning that requires contemplating more than two worlds and discuss applications of our results to counterfactual reasoning with a partially specified SCM that is coupled with data. We finally present empirical results that measure the gap between the complexities of counterfactual reasoning and associational/interventional reasoning on random SCMs.

The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.

Abstract--Change point detection is a crucial aspect of analyzing strategies it is necessary to identify momentum turning points, when time series data, as the presence of a change point indicates an a trend reverses from an uptrend to a downtrend such as in the 2020 abrupt and significant change in the process generating the data. While many algorithms for the problem of change point detection have been developed over time, it can be challenging to select This article presents an overview and comparison of algorithms the appropriate algorithm for a specific problem. The choice of commonly used for detecting change points in time series data. The the algorithm heavily depends on the nature of the problem and focus is on unsupervised change point detection, which involves the underlying data source. In this paper, we will exclusively segmenting the data without relying on large amounts of annotated examine unsupervised techniques due to their flexibility in the training data or the need to re-calibrate the model for each data application to various data sources without the requirement for source. The goal of this article is to help choosing the right detection abundant annotated training data and the re-calibration of the method for a particular application, with an emphasis on practical model. The examined methods will be introduced and evaluated aspects like the implementation and the calibration of the parameters. Our selection of methods aims for a good general performance for different data sources without fine tuning the algorithm.

Multi-robot navigation is the task of finding trajectories for a team of robotic agents to reach their destinations as quickly as possible without collisions. In this work, we introduce a new problem: fair-delay multi-robot navigation, which aims not only to enable such efficient, safe travels but also to equalize the travel delays among agents in terms of actual trajectories as compared to the best possible trajectories. The learning of a navigation policy to achieve this objective requires resolving a nontrivial credit assignment problem with robotic agents having continuous action spaces. Hence, we developed a new algorithm called Navigation with Counterfactual Fairness Filter (NCF2). With NCF2, each agent performs counterfactual inference on whether it can advance toward its goal or should stay still to let other agents go. Doing so allows us to effectively address the aforementioned credit assignment problem and improve fairness regarding travel delays while maintaining high efficiency and safety. Our extensive experimental results in several challenging multi-robot navigation environments demonstrate the greater effectiveness of NCF2 as compared to state-of-the-art fairness-aware multi-agent reinforcement learning methods. Our demo videos and code are available on the project webpage: https://omron-sinicx.github.io/ncf2/