Human-AI collaboration has the potential to transform various domains by leveraging the complementary strengths of human experts and Artificial Intelligence (AI) systems. However, unobserved confounding can undermine the effectiveness of this collaboration, leading to biased and unreliable outcomes. In this paper, we propose a novel solution to address unobserved confounding in human-AI collaboration by employing the marginal sensitivity model (MSM). Our approach combines domain expertise with AI-driven statistical modeling to account for potential confounders that may otherwise remain hidden. We present a deferral collaboration framework for incorporating the MSM into policy learning from observational data, enabling the system to control for the influence of unobserved confounding factors. In addition, we propose a personalized deferral collaboration system to leverage the diverse expertise of different human decision-makers. By adjusting for potential biases, our proposed solution enhances the robustness and reliability of collaborative outcomes. The empirical and theoretical analyses demonstrate the efficacy of our approach in mitigating unobserved confounding and improving the overall performance of human-AI collaborations.

Aligning Large Language Models (LLMs) with human preferences is crucial in ensuring desirable and controllable model behaviors.Current methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on the Bradley-Terry (B-T) model to maximize the likelihood of pairwise choices.However, when multiple responses are available, the B-T model fails to guarantee an accurate list ranking of the responses.To address this issue, we propose Permutative Preference Alignment (PPA), a novel offline listwise approach that incorporates the Normalized Discounted Cumulative Gain (NDCG)-a widely-used ranking metric-as an alternative training objective for LLM alignment.We develop an end-to-end alignment algorithm by approximating NDCG with a differentiable surrogate loss.Experiments demonstrate that PPA outperforms existing pairwise and listwise methods on evaluation sets and general benchmarks such as AlpacaEval.Furthermore, we show that NDCG-based approaches improve ranking accuracy more effectively than B-T-based methods and provide a theoretical explanation for this improvement.

We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator. SiD not only facilitates an exponentially fast reduction in Fréchet inception distance (FID) during distillation but also approaches or even exceeds the FID performance of the original teacher diffusion models. By reformulating forward diffusion processes as semi-implicit distributions, we leverage three score-related identities to create an innovative loss mechanism. This mechanism achieves rapid FID reduction by training the generator using its own synthesized images, eliminating the need for real data or reverse-diffusion-based generation, all accomplished within significantly shortened generation time. Upon evaluation across four benchmark datasets, the SiD algorithm demonstrates high iteration efficiency during distillation and surpasses competing distillation approaches, whether they are one-step or few-step, data-free, or dependent on training data, in terms of generation quality. This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation. The PyTorch implementation is available at https://github.com/mingyuanzhou/SiD.

Machine learning systems are widely used in many high-stakes contexts in which experimental designs for assigning treatments are infeasible. When evaluating decisions is costly, such as investigating fraud cases, or evaluating biopsy decisions, a sample-efficient strategy is needed. However, while existing active learning methods assume humans will always label the instances selected by the machine learning model, in many critical applications, humans may decline to label instances selected by the machine learning model due to reasons such as regulation constraint, domain knowledge, or algorithmic aversion, thus not sample efficient. In this paper, we study the Active Learning with Instance Rejection (ALIR) problem, which considers the human discretion behavior for high-stakes decision making problems. We propose new active learning algorithms under deep bayesian active learning for selective labeling (SEL-BALD) to address the ALIR problem. Our algorithms consider how to acquire information for both the machine learning model and the human discretion model. We conduct experiments on both synthetic and real-world datasets to demonstrate the effectiveness of our proposed algorithms.

This paper presents a new optimization approach to causal estimation. Given data that contains covariates and an outcome, which covariates are causes of the outcome, and what is the strength of the causality? In classical machine learning (ML), the goal of optimization is to maximize predictive accuracy. However, some covariates might exhibit a non-causal association with the outcome. Such spurious associations provide predictive power for classical ML, but they prevent us from causally interpreting the result. This paper proposes CoCo, an optimization algorithm that bridges the gap between pure prediction and causal inference. CoCo leverages the recently-proposed idea of environments, datasets of covariates/response where the causal relationships remain invariant but where the distribution of the covariates changes from environment to environment. Given datasets from multiple environments—and ones that exhibit sufficient heterogeneity—CoCo maximizes an objective for which the only solution is the causal solution. We describe the theoretical foundations of this approach and demonstrate its effectiveness on simulated and real datasets. Compared to classical ML and existing methods, CoCo provides more accurate estimates of the causal model and more accurate predictions under interventions.

Gradient estimation is often necessary for fitting generative models with discrete latent variables, in contexts such as reinforcement learning and variational autoencoder (VAE) training. The DisARM estimator achieves state of the art gradient variance for Bernoulli latent variable models in many contexts. However, DisARM and other estimators have potentially exploding variance near the boundary of the parameter space, where solutions tend to lie. To ameliorate this issue, we propose a new gradient estimator bitflip-1 that is lower variance at the boundaries of the parameter space. As bitflip-1 has complementary properties to existing estimators, we introduce an aggregated estimator, unbiased gradient variance clipping (UGC) that uses either a bitflip-1 or a DisARM gradient update for each coordinate. We theoretically prove that UGC has uniformly lower variance than DisARM. Empirically, we observe that UGC achieves the optimal value of the optimization objectives in toy experiments, discrete VAE training, and in a best subset selection problem.

This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. Given inputs, PCP constructs the predictive set based on random samples from an estimated generative model. It is efficient and compatible with conditional generative models with either explicit or implicit density functions. We show that PCP guarantees correct marginal coverage with finite samples and give empirical evidence of conditional coverage. We study PCP on a variety of simulated and real datasets. Compared to existing conformal prediction methods, PCP provides sharper predictive sets.

Mean-field variational inference (MFVI) has been widely applied in large scale Bayesian inference. However, MFVI assumes independent distribution on the latent variables, which often leads to objective functions with many local optima, making optimization algorithms sensitive to initialization. In this paper, we study the advantage of structured variational inference in the context of the two-class Stochastic Blockmodel. To facilitate theoretical analysis, the variational distribution is constructed to have a simple pairwise dependency structure on the nodes of the network. We prove that, in a broad density regime and for general random initializations, unlike MFVI, the estimated class labels by structured VI converge to the ground truth with high probability, when the model parameters are known, estimated within a reasonable range or jointly optimized with the variational parameters. In addition, empirically we demonstrate structured VI is more robust compared with MFVI when the graph is sparse and the signal to noise ratio is low. The paper takes a first step towards understanding the importance of dependency structure in variational inference for community detection.

Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension, making it challenging to apply existing on-policy gradient based deep RL algorithms efficiently. To effectively operate in multidimensional discrete action spaces, we construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. We follow rigorous statistical analysis to design how to generate and combine these correlated actions, and how to sparsify the gradients by shutting down the contributions from certain dimensions. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques. We demonstrate these properties on OpenAI Gym benchmark tasks, and illustrate how discretizing the action space could benefit the exploration phase and hence facilitate convergence to a better local optimal solution thanks to the flexibility of discrete policy.

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. Instead of solving the optimization for training relying on existing biased gradient estimators, an unbiased, low-variance gradient estimator, which evaluates the non-differentiable loss function over two correlated sets of binary hashing codes to control the gradient variance, is adopted to optimize the hashing function to achieve superior performance compared to the state-of-the-arts, as demonstrated by our comprehensive experiments.

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation under the Dirichlet distribution, then uses variable swapping to construct differently expressed but equivalent expectations, and finally shares common random numbers between these expectations to achieve significant variance reduction. Experimental results show ARSM closely resembles the performance of the true gradient for optimization in univariate settings; outperforms existing estimators by a large margin when applied to categorical variational auto-encoders; and provides a "try-and-see self-critic" variance reduction method for discrete-action policy gradient, which removes the need of estimating baselines by generating a random number of pseudo actions and estimating their action-value functions.

Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution. This mixing distribution can assume any density function, explicit or not, as long as independent random samples can be generated via reparameterization. Not only does SIVI expand the variational family to incorporate highly flexible variational distributions, including implicit ones that have no analytic density functions, but also sandwiches the evidence lower bound (ELBO) between a lower bound and an upper bound, and further derives an asymptotically exact surrogate ELBO that is amenable to optimization via stochastic gradient ascent. With a substantially expanded variational family and a novel optimization algorithm, SIVI is shown to closely match the accuracy of MCMC in inferring the posterior in a variety of Bayesian inference tasks.

In this paper, we study convergence properties of the gradient variant of Expectation-Maximization algorithm~\cite{lange1995gradient} for Gaussian Mixture Models for arbitrary number of clusters and mixing coefficients. We derive the convergence rate depending on the mixing coefficients, minimum and maximum pairwise distances between the true centers, dimensionality and number of components; and obtain a near-optimal local contraction radius. While there have been some recent notable works that derive local convergence rates for EM in the two symmetric mixture of Gaussians, in the more general case, the derivations need structurally different and non-trivial arguments. We use recent tools from learning theory and empirical processes to achieve our theoretical results.