We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an upper bound on the number of calls to the generative models needed for MDP-GapE to identify a near-optimal action with high probability. This problem-dependent sample complexity result is expressed in terms of the sub-optimality gaps of the state-action pairs that are visited during exploration. Our experiments reveal that MDP-GapE is also effective in practice, in contrast with other algorithms with sample complexity guarantees in the fixed-confidence setting, that are mostly theoretical.

In this paper, we present an improved analysis for dynamic regret of strongly convex and smooth functions. Specifically, we investigate the Online Multiple Gradient Descent (OMGD) algorithm proposed by Zhang et al. (2017). The original analysis shows that the dynamic regret of OMGD is at most $\mathcal{O}(\min\{\mathcal{P}_T,\mathcal{S}_T\})$, where $\mathcal{P}_T$ and $\mathcal{S}_T$ are path-length and squared path-length that measures the cumulative movement of minimizers of the online functions. We demonstrate that by an improved analysis, the dynamic regret of OMGD can be improved to $\mathcal{O}(\min\{\mathcal{P}_T,\mathcal{S}_T,\mathcal{V}_T\})$, where $\mathcal{V}_T$ is the function variation of the online functions. Note that the quantities of $\mathcal{P}_T, \mathcal{S}_T, \mathcal{V}_T$ essentially reflect different aspects of environmental non-stationarity---they are not comparable in general and are favored in different scenarios. Therefore, the dynamic regret presented in this paper actually achieves a \emph{best-of-three-worlds} guarantee and is strictly tighter than previous results.

The success of deep supervised learning depends on its automatic data representation abilities. Among all the characteristics of an ideal representation for high-dimensional complex data, information preservation, low dimensionality and disentanglement are the most essential ones. In this work, we propose a deep dimension reduction (DDR) approach to achieving a good data representation with these characteristics for supervised learning. At the population level, we formulate the ideal representation learning task as finding a nonlinear dimension reduction map that minimizes the sum of losses characterizing conditional independence and disentanglement. We estimate the target map at the sample level nonparametrically with deep neural networks. We derive a bound on the excess risk of the deep nonparametric estimator. The proposed method is validated via comprehensive numerical experiments and real data analysis in the context of regression and classification.

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when increasing the batch size to a substantial fraction of the training data for improving training time is the persistent degradation in performance (generalization gap). To address this issue, recent work propose to add small perturbations to the model parameters when computing the stochastic gradients and report improved generalization performance due to smoothing effects. However, this approach is poorly understood; it requires often model-specific noise and fine-tuning. To alleviate these drawbacks, we propose to use instead computationally efficient extrapolation (extragradient) to stabilize the optimization trajectory while still benefiting from smoothing to avoid sharp minima. This principled approach is well grounded from an optimization perspective and we show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer. We demonstrate that in a variety of experiments the scheme allows scaling to much larger batch sizes than before whilst reaching or surpassing SOTA accuracy.

Despite several important advances in recent years, learning causal structures represented by directed acyclic graphs (DAGs) remains a challenging task in high dimensional settings when the graphs to be learned are not sparse. In particular, the recent formulation of structure learning as a continuous optimization problem proved to have considerable advantages over the traditional combinatorial formulation, but the performance of the resulting algorithms is still wanting when the target graph is relatively large and dense. In this paper we propose a novel approach to mitigate this problem, by exploiting a low rank assumption regarding the (weighted) adjacency matrix of a DAG causal model. We establish several useful results relating interpretable graphical conditions to the low rank assumption, and show how to adapt existing methods for causal structure learning to take advantage of this assumption. We also provide empirical evidence for the utility of our low rank algorithms, especially on graphs that are not sparse. Not only do they outperform state-of-the-art algorithms when the low rank condition is satisfied, the performance on randomly generated scale-free graphs is also very competitive even though the true ranks may not be as low as is assumed.

A fundamental difficulty of causal learning is that causal models can generally not be fully identified based on observational data only. Interventional data, that is, data originating from different experimental environments, improves identifiability. However, the improvement depends critically on the target and nature of the interventions carried out in each experiment. Since in real applications experiments tend to be costly, there is a need to perform the right interventions such that as few as possible are required. In this work we propose a new active learning (i.e. experiment selection) framework (A-ICP) based on Invariant Causal Prediction (ICP) (Peters et al., 2016). For general structural causal models, we characterize the effect of interventions on so-called stable sets, a notion introduced by (Pfister et al., 2019). We leverage these results to propose several intervention selection policies for A-ICP which quickly reveal the direct causes of a response variable in the causal graph while maintaining the error control inherent in ICP. Empirically, we analyze the performance of the proposed policies in both population and finite-regime experiments.

Training and inference efficiency of deep neural networks highly rely on the performance of tensor operators on hardware platforms. Manually optimized tensor operators have limitations in terms of supporting new operators or supporting new hardware platforms. Therefore, automatically optimizing device code configurations of tensor operators is getting increasingly attractive. However, current methods for tensor operator optimization usually suffer from poor sample-efficiency due to the combinatorial search space. In this work, we propose a novel evolutionary method, OpEvo, which efficiently explores the search spaces of tensor operators by introducing a topology-aware mutation operation based on q-random walk distribution to leverage the topological structures over the search spaces. Our comprehensive experiment results show that OpEvo can find the best configuration with the least number of trials and the lowest variance compared with state-of-the-art methods. All code of this work is available online.

The LSTM network was proposed to overcome the difficulty in learning long-term dependence, and has made significant advancements in applications. With its success and drawbacks in mind, this paper raises the question - do RNN and LSTM have long memory? We answer it partially by proving that RNN and LSTM do not have long memory from a statistical perspective. A new definition for long memory networks is further introduced, and it requires the model weights to decay at a polynomial rate. To verify our theory, we convert RNN and LSTM into long memory networks by making a minimal modification, and their superiority is illustrated in modeling long-term dependence of various datasets.

Latent variable models for multi-view learning attempt to find low-dimensional projections that fairly capture the correlations among multiple views that characterise each datum. High-dimensional views in medium-sized datasets and non-linear problems are traditionally handled by kernel methods, inducing a (non)-linear function between the latent projection and the data itself. However, they usually come with scalability issues and exposition to overfitting. To overcome these limitations, instead of imposing a kernel function, here we propose an alternative method. In particular, we combine probabilistic factor analysis with what we refer to as kernelized observations, in which the model focuses on reconstructing not the data itself, but its correlation with other data points measured by a kernel function. This model can combine several types of views (kernelized or not), can handle heterogeneous data and work in semi-supervised settings. Additionally, by including adequate priors, it can provide compact solutions for the kernelized observations (based in a automatic selection of bayesian support vectors) and can include feature selection capabilities. Using several public databases, we demonstrate the potential of our approach (and its extensions) w.r.t. common multi-view learning models such as kernel canonical correlation analysis or manifold relevance determination gaussian processes latent variable models.

A complex combination of simultaneous supervised-unsupervised learning is believed to be the key to humans performing tasks seamlessly across multiple domains or tasks. This phenomenon of cross-domain learning has been very well studied in domain adaptation literature. Recent domain adaptation works rely on an indirect way of first aligning the source and target domain distributions and then train a classifier on the labeled source domain to classify the target domain. However, this approach has the main drawback that obtaining a near-perfect alignment of the domains in itself might be difficult/impossible (e.g., language domains). To address this, we follow Vapnik's imperative of statistical learning that states any desired problem should be solved in the most direct way rather than solving a more general intermediate task and propose a direct approach to domain adaptation that does not require domain alignment. We propose a model referred Contradistinguisher that learns contrastive features and whose objective is to jointly learn to contradistinguish the unlabeled target domain in an unsupervised way and classify in a supervised way on the source domain. We achieve the state-of-the-art on Office-31 and VisDA-2017 datasets in both single-source and multi-source settings. We also demonstrate that the contradistinguish loss improves the model performance by increasing the shape bias.