Proceedings of machine learning research最新文献

A fundamental problem in data management is to find the elements in an array that match a query. Recently, learned indexes are being extensively used to solve this problem, where they learn a model to predict the location of the items in the array. They are empirically shown to outperform non-learned methods (e.g., B-trees or binary search that answer queries in $O\left(logn\right)$ time) by orders of magnitude. However, success of learned indexes has not been theoretically justified. Only existing attempt shows the same query time of $O\left(logn\right)$, but with a constant factor improvement in space complexity over non-learned methods, under some assumptions on data distribution. In this paper, we significantly strengthen this result, showing that under mild assumptions on data distribution, and the same space complexity as non-learned methods, learned indexes can answer queries in $O\left(loglogn\right)$ expected query time. We also show that allowing for slightly larger but still near-linear space overhead, a learned index can achieve $O\left(1\right)$ expected query time. Our results theoretically prove learned indexes are orders of magnitude faster than non-learned methods, theoretically grounding their empirical success.

A number of methods have been proposed for causal effect estimation, yet few have demonstrated efficacy in handling data with complex structures, such as images. To fill this gap, we propose Causal Multi-task Deep Ensemble (CMDE), a novel framework that learns both shared and group-specific information from the study population. We provide proofs demonstrating equivalency of CDME to a multi-task Gaussian process (GP) with a coregionalization kernel a priori. Compared to multi-task GP, CMDE efficiently handles high-dimensional and multi-modal covariates and provides pointwise uncertainty estimates of causal effects. We evaluate our method across various types of datasets and tasks and find that CMDE outperforms state-of-the-art methods on a majority of these tasks.

Deep offline reinforcement learning has recently demonstrated considerable promises in leveraging offline datasets, providing high-quality models that significantly reduce the online interactions required for fine-tuning. However, such a benefit is often diminished due to the marked state-action distribution shift, which causes significant bootstrap error and wipes out the good initial policy Existing solutions resort to constraining the policy shift or balancing the sample replay based on their online-ness. However, they require online estimation of distribution divergence or density ratio. To avoid such complications, we propose deviating from existing actor-critic approaches that directly transfer the state-action value functions. Instead, we post-process them by aligning with the offline learned policy, so that the $Q$ -values for actions outside the offline policy are also tamed. As a result, the online fine-tuning can be simply performed as in the standard actor-critic algorithms. We show empirically that the proposed method improves the performance of the fine-tuned robotic agents on various simulated tasks.

Conditional randomization tests (CRTs) assess whether a variable $x$ is predictive of another variable $y$, having observed covariates $z$. CRTs require fitting a large number of predictive models, which is often computationally intractable. Existing solutions to reduce the cost of CRTs typically split the dataset into a train and test portion, or rely on heuristics for interactions, both of which lead to a loss in power. We propose the decoupled independence test (DIET), an algorithm that avoids both of these issues by leveraging marginal independence statistics to test conditional independence relationships. DIET tests the marginal independence of two random variables: $F_{x\mid z}(x\mid z)$ and $F_{y\mid z}(y\mid z)$ where $F_{\cdot \mid z}(\cdot \mid z)$ is a conditional cumulative distribution function (CDF) for the distribution $p(\cdot \mid z)$. These variables are termed "information residuals." We give sufficient conditions for DIET to achieve finite sample type-1 error control and power greater than the type-1 error rate. We then prove that when using the mutual information between the information residuals as a test statistic, DIET yields the most powerful conditionally valid test. Finally, we show DIET achieves higher power than other tractable CRTs on several synthetic and real benchmarks.

The recently proposed identifiable variational autoencoder (iVAE) framework provides a promising approach for learning latent independent components (ICs). iVAEs use auxiliary covariates to build an identifiable generation structure from covariates to ICs to observations, and the posterior network approximates ICs given observations and covariates. Though the identifiability is appealing, we show that iVAEs could have local minimum solution where observations and the approximated ICs are independent given covariates.-a phenomenon we referred to as the posterior collapse problem of iVAEs. To overcome this problem, we develop a new approach, covariate-informed iVAE (CI-iVAE) by considering a mixture of encoder and posterior distributions in the objective function. In doing so, the objective function prevents the posterior collapse, resulting latent representations that contain more information of the observations. Furthermore, CI-iVAE extends the original iVAE objective function to a larger class and finds the optimal one among them, thus having tighter evidence lower bounds than the original iVAE. Experiments on simulation datasets, EMNIST, Fashion-MNIST, and a large-scale brain imaging dataset demonstrate the effectiveness of our new method.

Offline reinforcement learning (RL) is a promising approach for training intelligent medical agents to learn treatment policies and assist decision making in many healthcare applications, such as scheduling clinical visits and assigning dosages for patients with chronic conditions. In this paper, we investigate the potential usefulness of Decision Transformer (Chen et al., 2021)-a new offline RL paradigm-in medical domains where decision making in continuous time is desired. As Decision Transformer only handles discrete-time (or turn-based) sequential decision making scenarios, we generalize it to Continuous-Time Decision Transformer that not only considers the past clinical measurements and treatments but also the timings of previous visits, and learns to suggest the timings of future visits as well as the treatment plan at each visit. Extensive experiments on synthetic datasets and simulators motivated by real-world medical applications demonstrate that Continuous-Time Decision Transformer is able to outperform competitors and has clinical utility in terms of improving patients' health and prolonging their survival by learning high-performance policies from logged data generated using policies of different levels of quality.

Domain scientists interested in causal mechanisms are usually limited by the frequency at which they can collect the measurements of social, physical, or biological systems. A common and plausible assumption is that higher measurement frequencies are the only way to gain more informative data about the underlying dynamical causal structure. This assumption is a strong driver for designing new, faster instruments, but such instruments might not be feasible or even possible. In this paper, we show that this assumption is incorrect: there are situations in which we can gain additional information about the causal structure by measuring more slowly than our current instruments. We present an algorithm that uses graphs at multiple measurement timescales to infer underlying causal structure, and show that inclusion of structures at slower timescales can nonetheless reduce the size of the equivalence class of possible causal structures. We provide simulation data about the probability of cases in which deliberate undersampling yields a gain, as well as the size of this gain.