Studying the properties of stochastic noise to optimize complex non-convex functions has been an active area of research in the field of machine learning. Prior work has shown that the noise of stochastic gradient descent improves optimization by overcoming undesirable obstacles in the landscape. Moreover, injecting artificial Gaussian noise has become a popular idea to quickly escape saddle points. Indeed, in the absence of reliable gradient information, the noise is used to explore the landscape, but it is unclear what type of noise is optimal in terms of exploration ability. In order to narrow this gap in our knowledge, we study a general type of continuous-time non-Markovian process, based on fractional Brownian motion, that allows for the increments of the process to be correlated. This generalizes processes based on Brownian motion, such as the Ornstein-Uhlenbeck process. We demonstrate how to discretize such processes which gives rise to the new algorithm fPGD. This method is a generalization of the known algorithms PGD and Anti-PGD. We study the properties of fPGD both theoretically and empirically, demonstrating that it possesses exploration abilities that, in some cases, are favorable over PGD and Anti-PGD. These results open the field to novel ways to exploit noise for training machine learning models.

Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates which can be false positive or similar to the ground-truth label. In this paper, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling large number of candidate structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and non-candidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n-slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of Natural Language Processing show the effectiveness of the proposed model.

Large Transformer models achieved the state-of-the-art status for Natural Language Understanding tasks and are increasingly becoming the baseline model architecture for modeling source code. Transformers are usually pre-trained on large unsupervised corpora, learning token representations and transformations relevant to modeling generally available text, and are then fine-tuned on a particular downstream task of interest. While fine-tuning is a tried-and-true method for adapting a model to a new domain -- for example, question-answering on a given topic -- generalization remains an on-going challenge. In this paper, we explore and evaluate transformer model fine-tuning for personalization. In the context of generating unit tests for Java methods, we evaluate learning to personalize to a specific software project using several personalization techniques. We consider three key approaches: (i) custom fine-tuning, which allows all the model parameters to be tuned; (ii) lightweight fine-tuning, which freezes most of the model's parameters, allowing tuning of the token embeddings and softmax layer only or the final layer alone; (iii) prefix tuning, which keeps model parameters frozen, but optimizes a small project-specific prefix vector. Each of these techniques offers a trade-off in total compute cost and predictive performance, which we evaluate by code and task-specific metrics, training time, and total computational operations. We compare these fine-tuning strategies for code generation and discuss the potential generalization and cost benefits of each in various deployment scenarios.

Existing partial sequence labeling models mainly focus on max-margin framework which fails to provide an uncertainty estimation of the prediction. Further, the unique ground truth disambiguation strategy employed by these models may include wrong label information for parameter learning. In this paper, we propose structured Gaussian Processes for partial sequence labeling (SGPPSL), which encodes uncertainty in the prediction and does not need extra effort for model selection and hyperparameter learning. The model employs factor-as-piece approximation that divides the linear-chain graph structure into the set of pieces, which preserves the basic Markov Random Field structure and effectively avoids handling large number of candidate output sequences generated by partially annotated data. Then confidence measure is introduced in the model to address different contributions of candidate labels, which enables the ground-truth label information to be utilized in parameter learning. Based on the derived lower bound of the variational lower bound of the proposed model, variational parameters and confidence measures are estimated in the framework of alternating optimization. Moreover, weighted Viterbi algorithm is proposed to incorporate confidence measure to sequence prediction, which considers label ambiguity arose from multiple annotations in the training data and thus helps improve the performance. SGPPSL is evaluated on several sequence labeling tasks and the experimental results show the effectiveness of the proposed model.

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item" as a feature is predictive of "user purchased this item" in the offline data, but is clearly not available during online serving. Another source of privileged features is those that are too expensive to compute online but feasible to be added offline. Privileged features distillation (PFD) refers to a natural idea: train a "teacher" model using all features (including privileged ones) and then use it to train a "student" model that does not use the privileged features. In this paper, we first study PFD empirically on three public ranking datasets and an industrial-scale ranking problem derived from Amazon's logs. We show that PFD outperforms several baselines (no-distillation, pretraining-finetuning, self-distillation, and generalized distillation) on all these datasets. Next, we analyze why and when PFD performs well via both empirical ablation studies and theoretical analysis for linear models. Both investigations uncover an interesting non-monotone behavior: as the predictive power of a privileged feature increases, the performance of the resulting student model initially increases but then decreases. We show the reason for the later decreasing performance is that a very predictive privileged teacher produces predictions with high variance, which lead to high variance student estimates and inferior testing performance.

Visible-infrared person re-identification (ReID) aims to recognize a same person of interest across a network of RGB and IR cameras. Some deep learning (DL) models have directly incorporated both modalities to discriminate persons in a joint representation space. However, this cross-modal ReID problem remains challenging due to the large domain shift in data distributions between RGB and IR modalities. This paper introduces a novel approach for a creating intermediate virtual domain that acts as bridges between the two main domains (i.e., RGB and IR modalities) during training. This intermediate domain is considered as privileged information (PI) that is unavailable at test time, and allows formulating this cross-modal matching task as a problem in learning under privileged information (LUPI). We devised a new method to generate images between visible and infrared domains that provide additional information to train a deep ReID model through an intermediate domain adaptation. In particular, by employing color-free and multi-step triplet loss objectives during training, our method provides common feature representation spaces that are robust to large visible-infrared domain shifts. Experimental results on challenging visible-infrared ReID datasets indicate that our proposed approach consistently improves matching accuracy, without any computational overhead at test time.

Despite achieving accuracies higher than 90% on recognizing upper-limb movements through sEMG (surface Electromyography) signal with the state of art classifiers in the laboratory environment, there are still issues to be addressed for a myo-controlled prosthesis achieve similar performance in real environment conditions. Thereby, the main goal of this review is to expose the latest researches in terms of strategies in each block of the system, giving a global view of the current state of academic research. A systematic review was conducted, and the retrieved papers were organized according to the system step related to the proposed method. Then, for each stage of the upper limb motion recognition system, the works were described and compared in terms of strategy, methodology and issue addressed. An additional section was destined for the description of works related to signal contamination that is often neglected in reviews focused on sEMG based motion classifiers. Therefore, this section is the main contribution of this paper. Deep learning methods are a current trend for classification stage, providing strategies based on time-series and transfer learning to address the issues related to limb position, temporal/inter-subject variation, and electrode displacement. Despite the promising strategies presented for contaminant detection, identification, and removal, there are still some factors to be considered, such as the occurrence of simultaneous contaminants.

Magnetic Resonance Fingerprinting (MRF) is a novel technique that simultaneously estimates multiple tissue-related parameters, such as the longitudinal relaxation time T1, the transverse relaxation time T2, off resonance frequency B0 and proton density, from a scanned object in just tens of seconds. However, the MRF method suffers from aliasing artifacts because it significantly undersamples the k-space data. In this work, we propose a compressed sensing (CS) framework for simultaneously estimating multiple tissue-related parameters based on the MRF method. It is more robust to low sampling ratio and is therefore more efficient in estimating MR parameters for all voxels of an object. Furthermore, the MRF method requires identifying the nearest atoms of the query fingerprints from the MR-signal-evolution dictionary with the L2 distance. However, we observed that the L2 distance is not always a proper metric to measure the similarities between MR Fingerprints. Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints. Numerical results on extensive simulated cases show that our method substantially outperforms stateof-the-art methods in terms of accuracy of parameter estimation.

This paper presents the HiPart package, an open-source native python library that provides efficient and interpret-able implementations of divisive hierarchical clustering algorithms. HiPart supports interactive visualizations for the manipulation of the execution steps allowing the direct intervention of the clustering outcome. This package is highly suited for Big Data applications as the focus has been given to the computational efficiency of the implemented clustering methodologies. The dependencies used are either Python build-in packages or highly maintained stable external packages. The software is provided under the MIT license.

Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot Classification (FSC), recent works explore the feature distributions aiming at maximizing likelihoods or posteriors with respect to the unknown parameters. Following this vein, and considering the parallel between FSC and clustering, we seek for better taking into account the uncertainty in estimation due to lack of data, as well as better statistical properties of the clusters associated with each class. Therefore in this paper we propose a new clustering method based on Variational Bayesian inference, further improved by Adaptive Dimension Reduction based on Probabilistic Linear Discriminant Analysis. Our proposed method significantly improves accuracy in the realistic unbalanced transductive setting on various Few-Shot benchmarks when applied to features used in previous studies, with a gain of up to $6\%$ in accuracy. In addition, when applied to balanced setting, we obtain very competitive results without making use of the class-balance artefact which is disputable for practical use cases. We also provide the performance of our method on a high performing pretrained backbone, with the reported results further surpassing the current state-of-the-art accuracy, suggesting the genericity of the proposed method.