Enhancing the diversity of policies is beneficial for robustness, exploration, and transfer in reinforcement learning (RL). In this paper, we aim to seek diverse policies in an under-explored setting, namely RL tasks with structured action spaces with the two properties of composability and local dependencies. The complex action structure, non-uniform reward landscape, and subtle hyperparameter tuning due to the properties of structured actions prevent existing approaches from scaling well. We propose a simple and effective RL method, Diverse Policy Optimization (DPO), to model the policies in structured action space as the energy-based models (EBM) by following the probabilistic RL framework. A recently proposed novel and powerful generative model, GFlowNet, is introduced as the efficient, diverse EBM-based policy sampler. DPO follows a joint optimization framework: the outer layer uses the diverse policies sampled by the GFlowNet to update the EBM-based policies, which supports the GFlowNet training in the inner layer. Experiments on ATSC and Battle benchmarks demonstrate that DPO can efficiently discover surprisingly diverse policies in challenging scenarios and substantially outperform existing state-of-the-art methods.

Malignant mesothelioma is classified into three histological subtypes, Epithelioid, Sarcomatoid, and Biphasic according to the relative proportions of epithelioid and sarcomatoid tumor cells present. Biphasic tumors display significant populations of both cell types. This subtyping is subjective and limited by current diagnostic guidelines and can differ even between expert thoracic pathologists when characterising the continuum of relative proportions of epithelioid and sarcomatoid components using a three class system. In this work, we develop a novel dual-task Graph Neural Network (GNN) architecture with ranking loss to learn a model capable of scoring regions of tissue down to cellular resolution. This allows quantitative profiling of a tumor sample according to the aggregate sarcomatoid association score of all the cells in the sample. The proposed approach uses only core-level labels and frames the prediction task as a dual multiple instance learning (MIL) problem. Tissue is represented by a cell graph with both cell-level morphological and regional features. We use an external multi-centric test set from Mesobank, on which we demonstrate the predictive performance of our model. We validate our model predictions through an analysis of the typical morphological features of cells according to their predicted score, finding that some of the morphological differences identified by our model match known differences used by pathologists. We further show that the model score is predictive of patient survival with a hazard ratio of 2.30. The code for the proposed approach, along with the dataset, is available at: https://github.com/measty/MesoGraph.

Recovering a globally accurate complex physics field from limited sensor is critical to the measurement and control in the aerospace engineering. General reconstruction methods for recovering the field, especially the deep learning with more parameters and better representational ability, usually require large amounts of labeled data which is unaffordable. To solve the problem, this paper proposes Uncertainty Guided Ensemble Self-Training (UGE-ST), using plentiful unlabeled data to improve reconstruction performance. A novel self-training framework with the ensemble teacher and pretraining student designed to improve the accuracy of the pseudo-label and remedy the impact of noise is first proposed. On the other hand, uncertainty-guided learning is proposed to encourage the model to focus on the highly confident regions of pseudo-labels and mitigate the effects of wrong pseudo-labeling in self-training, improving the performance of the reconstruction model. Experiments include the pressure velocity field reconstruction of airfoil and the temperature field reconstruction of aircraft system indicate that our UGE-ST can save up to 90% of the data with the same accuracy as supervised learning.

Despite being conceptually attractive, kNN-MT is burdened with massive storage requirements and high computational complexity since it conducts nearest neighbor searches over the entire reference corpus. In this paper, we propose a simple and scalable nearest neighbor machine translation framework to drastically promote the decoding and storage efficiency of kNN-based models while maintaining the translation performance. To this end, we dynamically construct an extremely small datastore for each input via sentence-level retrieval to avoid searching the entire datastore in vanilla kNN-MT, based on which we further introduce a distance-aware adapter to adaptively incorporate the kNN retrieval results into the pre-trained NMT models. Experiments on machine translation in two general settings, static domain adaptation, and online learning, demonstrate that our proposed approach not only achieves almost 90% speed as the NMT model without performance degradation, but also significantly reduces the storage requirements of kNN-MT. Domain adaptation is one of the fundamental challenges in machine learning which aspires to cope with the discrepancy across domain distributions and improve the generality of the trained models. It has attracted wide attention in the neural machine translation (NMT) area (Britz et al., 2017; Chen et al., 2017; Chu & Wang, 2018; Bapna & Firat, 2019; Bapna et al., 2019; Wei et al., 2020). Recently, kNN-MT and its variants (Khandelwal et al., 2021; Zheng et al., 2021a;b; Wang et al., 2022a) provide a new paradigm and have achieved remarkable performance for fast domain adaptation by retrieval pipelines. These approaches combine traditional NMT models (Bahdanau et al., 2015; Vaswani et al., 2017) with a token-level k-nearest-neighbour (kNN) retrieval mechanism, allowing it to directly access the domain-specific datastore to improve translation accuracy without fine-tuning the entire model.

Specifying reward functions for complex tasks like object manipulation or driving is challenging to do by hand. Reward learning seeks to address this by learning a reward model using human feedback on selected query policies. This shifts the burden of reward specification to the optimal design of the queries. We propose a theoretical framework for studying reward learning and the associated optimal experiment design problem. Our framework models rewards and policies as nonparametric functions belonging to subsets of Reproducing Kernel Hilbert Spaces (RKHSs). The learner receives (noisy) oracle access to a true reward and must output a policy that performs well under the true reward. For this setting, we first derive non-asymptotic excess risk bounds for a simple plug-in estimator based on ridge regression. We then solve the query design problem by optimizing these risk bounds with respect to the choice of query set and obtain a finite sample statistical rate, which depends primarily on the eigenvalue spectrum of a certain linear operator on the RKHSs. Despite the generality of these results, our bounds are stronger than previous bounds developed for more specialized problems. We specifically show that the well-studied problem of Gaussian process (GP) bandit optimization is a special case of our framework, and that our bounds either improve or are competitive with known regret guarantees for the Mat\'ern kernel.

In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. This work offers a partial reconciliation between the two by establishing a correspondence between Shapley Values and Generalized Additive Models (GAMs). We introduce $n$-Shapley Values, a parametric family of local post-hoc explanation algorithms that explain individual predictions with interaction terms up to order $n$. By varying the parameter $n$, we obtain a sequence of explanations that covers the entire range from Shapley Values up to a uniquely determined decomposition of the function we want to explain. The relationship between $n$-Shapley Values and this decomposition offers a functionally-grounded characterization of Shapley Values, which highlights their limitations. We then show that $n$-Shapley Values, as well as the Shapley Taylor- and Faith-Shap interaction indices, recover GAMs with interaction terms up to order $n$. This implies that the original Shapely Values recover GAMs without variable interactions. Taken together, our results provide a precise characterization of Shapley Values as they are being used in explainable machine learning. They also offer a principled interpretation of partial dependence plots of Shapley Values in terms of the underlying functional decomposition. A package for the estimation of different interaction indices is available at \url{https://github.com/tml-tuebingen/nshap}.

Online optimization is a well-established optimization paradigm that aims to make a sequence of correct decisions given knowledge of the correct answer to previous decision tasks. Bilevel programming involves a hierarchical optimization problem where the feasible region of the so-called outer problem is restricted by the graph of the solution set mapping of the inner problem. This paper brings these two ideas together and studies an online bilevel optimization setting in which a sequence of time-varying bilevel problems are revealed one after the other. We extend the known regret bounds for single-level online algorithms to the bilevel setting. Specifically, we introduce new notions of bilevel regret, develop an online alternating time-averaged gradient method that is capable of leveraging smoothness, and provide regret bounds in terms of the path-length of the inner and outer minimizer sequences.

The introduction of machine learning (ML) techniques to the field of survival analysis has increased the flexibility of modeling approaches, and ML based models have become state-of-the-art. These models optimize their own cost functions, and their performance is often evaluated using the concordance index (C-index). From a statistical learning perspective, it is therefore an important problem to analyze the relationship between the optimizers of the C-index and those of the ML cost functions. We address this issue by providing C-index Fisher-consistency results and excess risk bounds for several of the commonly used cost functions in survival analysis. We identify conditions under which they are consistent, under the form of three nested families of survival models. We also study the general case where no model assumption is made and present a new, off-the-shelf method that is shown to be consistent with the C-index, although computationally expensive at inference. Finally, we perform limited numerical experiments with simulated data to illustrate our theoretical findings.

Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most problems are solved in discrete time, the underlying process is often continuous in nature. We exploit this underlying continuity by developing predictor-corrector algorithms for time-varying stochastic optimizations. We provide error bounds for the iterates, both in presence of pure and noisy access to the queries from the relevant derivatives of the loss function. Furthermore, we show (theoretically and empirically in several examples) that our method outperforms non-predictor corrector methods that do not exploit the underlying continuous process.

It is quite obvious that ML teams developing new models or algorithms expect that the performance of the model on test data will be optimal. But many times that just doesn't happen. The above list is not exhaustive though. In this article, we'll discuss the process which can solve multiple above-mentioned problems and ML teams be very mindful while executing it. It is widely accepted in the machine learning community that preprocessing data is an important step in the ML workflow and it can improve the performance of the model. "A study by Bezdek et al. (1984) found that preprocessing the data improved the accuracy of several clustering algorithms by up to 50%." "A study by Chollet (2018) found that data preprocessing techniques such as data normalization and data augmentation can improve the performance of deep learning models."