For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood estimation, it compromises on the ability to tune language models to easily maximize non-differentiable and non-binary objectives according to the LLM designer's preferences (e.g., using simpler language or minimizing specific kinds of harmful content). These may neither align with user preferences nor even be able to be captured tractably by binary preference data. To leverage the simplicity and performance of DPO with the generalizability of RL, we propose a hybrid approach between DPO and RLHF. With a simple augmentation to the implicit reward decomposition of DPO, we allow for tuning LLMs to maximize a set of arbitrary auxiliary rewards using offline RL. The proposed method, Hybrid Preference Optimization (HPO), shows the ability to effectively generalize to both user preferences and auxiliary designer objectives, while preserving alignment performance across a range of challenging benchmarks and model sizes.

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more classical literature of statistical machine learning, many models have sequential Bayesian update rules that yield the same learning outcome as the batch training, i.e., they are completely immune to catastrophic forgetting. However, they are often overly simple to model complex real-world data. In this work, we adopt the meta-learning paradigm to combine the strong representational power of neural networks and simple statistical models' robustness to forgetting. In our novel meta-continual learning framework, continual learning takes place only in statistical models via ideal sequential Bayesian update rules, while neural networks are meta-learned to bridge the raw data and the statistical models. Since the neural networks remain fixed during continual learning, they are protected from catastrophic forgetting. This approach not only achieves significantly improved performance but also exhibits excellent scalability. Since our approach is domain-agnostic and model-agnostic, it can be applied to a wide range of problems and easily integrated with existing model architectures.

In applied statistics and machine learning, the "gold standards" used for training are often biased and almost always noisy. Dawid and Skene's justifiably popular crowdsourcing model adjusts for rater (coder, annotator) sensitivity and specificity, but fails to capture distributional properties of rating data gathered for training, which in turn biases training. In this study, we introduce a general purpose measurement-error model with which we can infer consensus categories by adding item-level effects for difficulty, discriminativeness, and guessability. We further show how to constrain the bimodal posterior of these models to avoid (or if necessary, allow) adversarial raters. We validate our model's goodness of fit with posterior predictive checks, the Bayesian analogue of $\chi^2$ tests. Dawid and Skene's model is rejected by goodness of fit tests, whereas our new model, which adjusts for item heterogeneity, is not rejected. We illustrate our new model with two well-studied data sets, binary rating data for caries in dental X-rays and implication in natural language.

Diffusion models (DMs) have recently shown outstanding capability in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems. However, most existing DM-based methods rely on approximations in the generative process to be generic to different inverse problems, leading to inaccurate sample distributions that deviate from the target posterior defined within the Bayesian framework. To harness the generative power of DMs while avoiding such approximations, we propose a Markov chain Monte Carlo algorithm that performs posterior sampling for general inverse problems by reducing it to sampling the posterior of a Gaussian denoising problem. Crucially, we leverage a general DM formulation as a unified interface that allows for rigorously solving the denoising problem with a range of state-of-the-art DMs. We demonstrate the effectiveness of the proposed method on six inverse problems (three linear and three nonlinear), including a real-world black hole imaging problem. Experimental results indicate that our proposed method offers more accurate reconstructions and posterior estimation compared to existing DM-based imaging inverse methods.

This paper investigates sparse high-dimensional linear regression, particularly examining the properties of the posterior under conditions of random design and unknown error variance. We provide consistency results for the posterior and analyze its concentration rates, demonstrating adaptiveness to the unknown sparsity level of the regression coefficient vector. Furthermore, we extend our investigation to establish concentration outcomes for parameter estimation using specific distance measures. These findings are in line with recent discoveries in frequentist studies. Additionally, by employing techniques to address model misspecification through a fractional posterior, we broaden our analysis through oracle inequalities to encompass the critical aspect of model misspecification for the regular posterior. Our novel findings are demonstrated using two different types of sparsity priors: a shrinkage prior and a spike-and-slab prior.

Real-world decision-making requires grappling with a perpetual lack of data as environments change; intelligent agents must comprehend uncertainty and actively gather information to resolve it. We propose a new framework for learning bandit algorithms from massive historical data, which we demonstrate in a cold-start recommendation problem. First, we use historical data to pretrain an autoregressive model to predict a sequence of repeated feedback/rewards (e.g., responses to news articles shown to different users over time). In learning to make accurate predictions, the model implicitly learns an informed prior based on rich action features (e.g., article headlines) and how to sharpen beliefs as more rewards are gathered (e.g., clicks as each article is recommended). At decision-time, we autoregressively sample (impute) an imagined sequence of rewards for each action, and choose the action with the largest average imputed reward. Far from a heuristic, our approach is an implementation of Thompson sampling (with a learned prior), a prominent active exploration algorithm. We prove our pretraining loss directly controls online decision-making performance, and we demonstrate our framework on a news recommendation task where we integrate end-to-end fine-tuning of a pretrained language model to process news article headline text to improve performance.

Balancing the exploration-exploitation trade-off is a fundamental dilemma in reinforcement learning (RL). This issue has been systemically addressed in two main approaches, namely optimism in the face of uncertainty (OFU) and Thompson sampling (TS). The methods using OFU first construct confidence sets for the environment or model parameters given the samples observed so far. After finding the reward-maximizing or optimistic parameters within the confidence set, an optimal policy with respect to the parameters is constructed and executed [1]. Various algorithms using OFU are shown to have strong theoretical guarantees in bandits [2]. On the other hand, TS is a Bayesian method in which environment or model parameters are sampled from the posterior that is updated along the process using samples and a prior, and an optimal policy with respect to the sampled parameter is constructed and executed [3].

Explainable AI Planning (XAIP) aims to develop AI agents that can effectively explain their decisions and actions to human users, fostering trust and facilitating human-AI collaboration. A key challenge in XAIP is model reconciliation, which seeks to align the mental models of AI agents and humans. While existing approaches often assume a known and deterministic human model, this simplification may not capture the complexities and uncertainties of real-world interactions. In this paper, we propose a novel framework that enables AI agents to learn and update a probabilistic human model through argumentation-based dialogues. Our approach incorporates trust-based and certainty-based update mechanisms, allowing the agent to refine its understanding of the human's mental state based on the human's expressed trust in the agent's arguments and certainty in their own arguments. We employ a probability weighting function inspired by prospect theory to capture the relationship between trust and perceived probability, and use a Bayesian approach to update the agent's probability distribution over possible human models. We conduct a human-subject study to empirically evaluate the effectiveness of our approach in an argumentation scenario, demonstrating its ability to capture the dynamics of human belief formation and adaptation.

We derive a novel, provably robust, and closed-form Bayesian update rule for online filtering in state-space models in the presence of outliers and misspecified measurement models. Our method combines generalised Bayesian inference with filtering methods such as the extended and ensemble Kalman filter. We use the former to show robustness and the latter to ensure computational efficiency in the case of nonlinear models. Our method matches or outperforms other robust filtering methods (such as those based on variational Bayes) at a much lower computational cost. We show this empirically on a range of filtering problems with outlier measurements, such as object tracking, state estimation in high-dimensional chaotic systems, and online learning of neural networks.

A career is a crucial aspect for any person to fulfill their desires through hard work. During their studies, students cannot find the best career suggestions unless they receive meaningful guidance tailored to their skills. Therefore, we developed an AI-assisted model for early prediction to provide better career suggestions. Although the task is difficult, proper guidance can make it easier. Effective career guidance requires understanding a student's academic skills, interests, and skill-related activities. In this research, we collected essential information from Computer Science (CS) and Software Engineering (SWE) students to train a machine learning (ML) model that predicts career paths based on students' career-related information. To adequately train the models, we applied Natural Language Processing (NLP) techniques and completed dataset pre-processing. For comparative analysis, we utilized multiple classification ML algorithms and deep learning (DL) algorithms. This study contributes valuable insights to educational advising by providing specific career suggestions based on the unique features of CS and SWE students. Additionally, the research helps individual CS and SWE students find suitable jobs that match their skills, interests, and skill-related activities.