In this paper, we compare the performances of traditional machine learning models using feature engineering and word vectors and the state-of-the-art language model BERT using word embeddings on three datasets. We also consider the time and cost efficiency of feature engineering compared to BERT. From our results we conclude that the use of the BERT model was only worth the time and cost trade-off for one of the three datasets we used for comparison, where the BERT model significantly outperformed any kind of traditional classifier that uses feature vectors, instead of embeddings. Using the BERT model for the other datasets only achieved an increase of 0.03 and 0.05 of accuracy and F1 score respectively, which could be argued makes its use not worth the time and cost of GPU.

The universal-set naive Bayes classifier (UNB)~\cite{Komiya:13}, defined using likelihood ratios (LRs), was proposed to address imbalanced classification problems. However, the LR estimator used in the UNB overestimates LRs for low-frequency data, degrading the classification performance. Our previous study~\cite{Kikuchi:19} proposed an effective LR estimator even for low-frequency data. This estimator uses regularization to suppress the overestimation, but we did not consider imbalanced data. In this paper, we integrated the estimator with the UNB. Our experiments with imbalanced data showed that our proposed classifier effectively adjusts the classification scores according to the class balance using regularization parameters and improves the classification performance.

Learning from imbalanced tabular data is a significant challenge in real-world classification tasks. In such cases, neural network performance is substantially impaired due to implicit bias toward the majority class. Existing solutions attempt to eliminate the bias through data re-sampling or re-weighting the loss in the learning process. Still, these methods tend to overfit the minority samples and perform poorly when the structure of the minority class is highly irregular. Here, we propose a novel deep meta-learning technique to augment a given imbalanced dataset with new minority instances. These additional data are incorporated during the classifier's training process, and their contributions are learned explicitly. The augmented samples are modified throughout the training to optimize the classifiers' average-precision score on a validation set. Multiple experiments with synthetic and real-world imbalanced datasets demonstrate the advantage of the proposed method, leading to a significant gap in comparison to many existing baselines.

In practical applications, data is used to make decisions in two steps: estimation and optimization. First, a machine learning model estimates parameters for a structural model relating decisions to outcomes. Second, a decision is chosen to optimize the structural model's predicted outcome as if its parameters were correctly estimated. Due to its flexibility and simple implementation, this ``estimate-then-optimize'' approach is often used for data-driven decision-making. Errors in the estimation step can lead estimate-then-optimize to sub-optimal decisions that result in regret, i.e., a difference in value between the decision made and the best decision available with knowledge of the structural model's parameters. We provide a novel bound on this regret for smooth and unconstrained optimization problems. Using this bound, in settings where estimated parameters are linear transformations of sub-Gaussian random vectors, we provide a general procedure for experimental design to minimize the regret resulting from estimate-then-optimize. We demonstrate our approach on simple examples and a pandemic control application.

Many network analysis and graph learning techniques are based on models of random walks which require to infer transition matrices that formalize the underlying stochastic process in an observed graph. For weighted graphs, it is common to estimate the entries of such transition matrices based on the relative weights of edges. However, we are often confronted with incomplete data, which turns the construction of the transition matrix based on a weighted graph into an inference problem. Moreover, we often have access to additional information, which capture topological constraints of the system, i.e. which edges in a weighted graph are (theoretically) possible and which are not, e.g. transportation networks, where we have access to passenger trajectories as well as the physical topology of connections, or a set of social interactions with the underlying social structure. Combining these two different sources of information to infer transition matrices is an open challenge, with implications on the downstream network analysis tasks. Addressing this issue, we show that including knowledge on such topological constraints can improve the inference of transition matrices, especially for small datasets. We derive an analytically tractable Bayesian method that uses repeated interactions and a topological prior to infer transition matrices data-efficiently. We compare it against commonly used frequentist and Bayesian approaches both in synthetic and real-world datasets, and we find that it recovers the transition probabilities with higher accuracy and that it is robust even in cases when the knowledge of the topological constraint is partial. Lastly, we show that this higher accuracy improves the results for downstream network analysis tasks like cluster detection and node ranking, which highlights the practical relevance of our method for analyses of various networked systems.

Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization. However, a number of techniques for fully discrete backpropagation could instead be applied. In this paper, we explore that direction and propose DAG-DB, a framework for learning DAGs by Discrete Backpropagation. Based on the architecture of Implicit Maximum Likelihood Estimation [I-MLE, arXiv:2106.01798], DAG-DB adopts a probabilistic approach to the problem, sampling binary adjacency matrices from an implicit probability distribution. DAG-DB learns a parameter for the distribution from the loss incurred by each sample, performing competitively using either of two fully discrete backpropagation techniques, namely I-MLE and Straight-Through Estimation.

Finding unified complexity measures and algorithms for sample-efficient learning is a central topic of research in reinforcement learning (RL). The Decision-Estimation Coefficient (DEC) is recently proposed by Foster et al. (2021) as a necessary and sufficient complexity measure for sample-efficient no-regret RL. This paper makes progress towards a unified theory for RL with the DEC framework. First, we propose two new DEC-type complexity measures: Explorative DEC (EDEC), and Reward-Free DEC (RFDEC). We show that they are necessary and sufficient for sample-efficient PAC learning and reward-free learning, thereby extending the original DEC which only captures no-regret learning. Next, we design new unified sample-efficient algorithms for all three learning goals. Our algorithms instantiate variants of the Estimation-To-Decisions (E2D) meta-algorithm with a strong and general model estimation subroutine. Even in the no-regret setting, our algorithm E2D-TA improves upon the algorithms of Foster et al. (2021) which require either bounding a variant of the DEC which may be prohibitively large, or designing problem-specific estimation subroutines. As applications, we recover existing and obtain new sample-efficient learning results for a wide range of tractable RL problems using essentially a single algorithm. We also generalize the DEC to give sample-efficient algorithms for all-policy model estimation, with applications for learning equilibria in Markov Games. Finally, as a connection, we re-analyze two existing optimistic model-based algorithms based on Posterior Sampling or Maximum Likelihood Estimation, showing that they enjoy similar regret bounds as E2D-TA under similar structural conditions as the DEC.

Machine Learning (ML) research has focused on maximizing the accuracy of predictive tasks. ML models, however, are increasingly more complex, resource intensive, and costlier to deploy in resource-constrained environments. These issues are exacerbated for prediction tasks with sequential classification on progressively transitioned stages with ''happens-before'' relation between them.We argue that it is possible to ''unfold'' a monolithic single multi-class classifier, typically trained for all stages using all data, into a series of single-stage classifiers. Each single-stage classifier can be cascaded gradually from cheaper to more expensive binary classifiers that are trained using only the necessary data modalities or features required for that stage. UnfoldML is a cost-aware and uncertainty-based dynamic 2D prediction pipeline for multi-stage classification that enables (1) navigation of the accuracy/cost tradeoff space, (2) reducing the spatio-temporal cost of inference by orders of magnitude, and (3) early prediction on proceeding stages. UnfoldML achieves orders of magnitude better cost in clinical settings, while detecting multi-stage disease development in real time. It achieves within 0.1% accuracy from the highest-performing multi-class baseline, while saving close to 20X on spatio-temporal cost of inference and earlier (3.5hrs) disease onset prediction. We also show that UnfoldML generalizes to image classification, where it can predict different level of labels (from coarse to fine) given different level of abstractions of a image, saving close to 5X cost with as little as 0.4% accuracy reduction.

Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes, dictionaries or parse trees. The contribution of the Zero Resource Speech Challenge series since 2015 has been to break down this long-term objective into four well-defined tasks -- Acoustic Unit Discovery, Spoken Term Discovery, Discrete Resynthesis, and Spoken Language Modeling -- and introduce associated metrics and benchmarks enabling model comparison and cumulative progress. We present an overview of the six editions of this challenge series since 2015, discuss the lessons learned, and outline the areas which need more work or give puzzling results.

We develop an R package SPQR that implements the semi-parametric quantile regression (SPQR) method in Xu and Reich (2021). The method begins by fitting a flexible density regression model using monotonic splines whose weights are modeled as data-dependent functions using artificial neural networks. Subsequently, estimates of conditional density and quantile process can all be obtained. Unlike many approaches to quantile regression that assume a linear model, SPQR allows for virtually any relationship between the covariates and the response distribution including non-linear effects and different effects on different quantile levels. To increase the interpretability and transparency of SPQR, model-agnostic statistics developed by Apley and Zhu (2020) are used to estimate and visualize the covariate effects and their relative importance on the quantile function. In this article, we detail how this framework is implemented in SPQR and illustrate how this package should be used in practice through simulated and real data examples.