Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models and learning from data. These methods scale to high-dimensional spaces and are effective at the non-convex optimizations often seen in robot learning. We look at sample-based methods from the perspective of inference-based control, specifically posterior policy iteration. From this perspective, we highlight how Gaussian noise priors produce rough control actions that are unsuitable for physical robot deployment. Considering smoother Gaussian process priors, as used in episodic reinforcement learning and motion planning, we demonstrate how smoother model predictive control can be achieved using online sequential inference. This inference is realized through an efficient factorization of the action distribution and a novel means of optimizing the likelihood temperature to improve importance sampling accuracy. We evaluate this approach on several high-dimensional robot control tasks, matching the sample efficiency of prior heuristic methods while also ensuring smoothness. Simulation results can be seen at https://monte-carlo-ppi.github.io/.

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic Gradient Descent (DP-SGD): 1) iterative perturbation and 2) gradient clipping. We propose a generic optimization framework, called {\em ModelMix}, which performs random aggregation of intermediate model states. It strengthens the composite privacy analysis utilizing the entropy of the training trajectory and improves the $(\epsilon, \delta)$ DP security parameters by an order of magnitude. We provide rigorous analyses for both the utility guarantees and privacy amplification of ModelMix. In particular, we present a formal study on the effect of gradient clipping in DP-SGD, which provides theoretical instruction on how hyper-parameters should be selected. We also introduce a refined gradient clipping method, which can further sharpen the privacy loss in private learning when combined with ModelMix. Thorough experiments with significant privacy/utility improvement are presented to support our theory. We train a Resnet-20 network on CIFAR10 with $70.4\%$ accuracy via ModelMix given $(\epsilon=8, \delta=10^{-5})$ DP-budget, compared to the same performance but with $(\epsilon=145.8,\delta=10^{-5})$ using regular DP-SGD; assisted with additional public low-dimensional gradient embedding, one can further improve the accuracy to $79.1\%$ with $(\epsilon=6.1, \delta=10^{-5})$ DP-budget, compared to the same performance but with $(\epsilon=111.2, \delta=10^{-5})$ without ModelMix.

To obtain a large amount of training labels inexpensively, researchers have recently adopted the weak supervision (WS) paradigm, which leverages labeling rules to synthesize training labels rather than using individual annotations to achieve competitive results for natural language processing (NLP) tasks. However, data imbalance is often overlooked in applying the WS paradigm, despite being a common issue in a variety of NLP tasks. To address this challenge, we propose Adaptive Ranking-based Sample Selection (ARS2), a model-agnostic framework to alleviate the data imbalance issue in the WS paradigm. Specifically, it calculates a probabilistic margin score based on the output of the current model to measure and rank the cleanliness of each data point. Then, the ranked data are sampled based on both class-wise and rule-aware ranking. In particular, the two sample strategies corresponds to our motivations: (1) to train the model with balanced data batches to reduce the data imbalance issue and (2) to exploit the expertise of each labeling rule for collecting clean samples. Experiments on four text classification datasets with four different imbalance ratios show that ARS2 outperformed the state-of-the-art imbalanced learning and WS methods, leading to a 2%-57.8% improvement on their F1-score.

Functional data analysis has long been used in modeling time series enabling long term predictions with the ability to We propose a novel group of Gaussian Process based algorithms work with irregularly sampled data [7]. In time series modeling, for fast approximate optimal stopping of time series with specific approaches based on Gaussian Processes (GPs) allow long term applications to financial markets. We show that structural properties forecasting in settings with small quantities of data for calibration commonly exhibited by financial time series (e.g., the tendency and those with a need to estimate the covariance of predictions [30, to mean-revert) allow the use of Gaussian and Deep Gaussian Process 17]. GPs also come up in finance when studying mean reverting models that further enable us to analytically evaluate optimal processes called Ornstein-Uhlenbeck (OU) processes which are GPs stopping value functions and policies. We additionally quantify with an exponential kernel [29].

We consider quantitative analyses of spectral data using laser-induced breakdown spectroscopy. We address the small size of training data available, and the validation of the predictions during inference on unknown data. For the purpose, we build robust calibration models using deep convolutional multitask learning architectures to predict the concentration of the analyte, alongside additional spectral information as auxiliary outputs. These secondary predictions can be used to validate the trustworthiness of the model by taking advantage of the mutual dependencies of the parameters of the multitask neural networks. Due to the experimental lack of training samples, we introduce a simulation-based data augmentation process to synthesise an arbitrary number of spectra, statistically representative of the experimental data. Given the nature of the deep learning model, no dimensionality reduction or data selection processes are required. The procedure is an end-to-end pipeline including the process of synthetic data augmentation, the construction of a suitable robust, homoscedastic, deep learning model, and the validation of its predictions. In the article, we compare the performance of the multitask model with traditional univariate and multivariate analyses, to highlight the separate contributions of each element introduced in the process.

The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model generalizes to new synthetic graphs, is robust to train-test distribution shifts, and achieves state-of-the-art performance on naturalistic graphs for low sample complexity.

Human visual reasoning allows us to leverage prior visual experience to recognize previously unseen Object-Attribute (O-A) relationships. Predicting such complex relationships of novel O-A compositions - referred to as Composition Zero Shot Learning (CZSL) [17, 19, 21, 22, 25, 28, 33, 36]-is an active area of research. There has been significant progress on CZSL methods in recent years, however, as our experiments demonstrate, their performance degrades in natural cluttered scenes, as illustrated in Fig.1. The main reason in these cases is the interference from the other potential confusing elements. For example, in Figure 1(B.1), the SOTA methods are not able to detect the object of interest given its size relative to image; and while the bird is the object of interest in Figure 1(B.2), the surrounding context dominated by the green leaves results in an incorrect association of the color attribute to the object. The poor performance of the SOTA methods can be attributed to the dominant confounding elements thereby impeding the right O-A composition prediction. This in turn is due to the bias towards seen O-A composition during training time. Generalization to more realistic cases as seen in Figure 1(B) is crucial for the widespread use of CZSL.

Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-friendly quantization constraints to train the model. We evaluate the two main classes of hardware-friendly quantization methods in the context of weight quantization: the traditional Mean Squared Quantization Error (MSQE)-based methods and the more recent gradient-based methods. We study the two methods on MobileNetV1 and MobileNetV2 using multiple empirical metrics to identify the sources of performance differences between the two classes, namely, sensitivity to outliers and convergence instability of the quantizer scaling factor. Using those insights, we propose various techniques to improve the performance of both quantization methods - they fix the optimization instability issues present in the MSQE-based methods during quantization of MobileNet models and allow us to improve validation performance of the gradient-based methods by 4.0% and 3.3% for MobileNetV1 and MobileNetV2 on ImageNet respectively.

Few-shot learning (Fei-Fei et al., 2006) aims to learn a new classification or regression model on a novel task that is not seen during training, given only a few examples in the novel task. Existing few-shot learning methods either rely on episodic meta-learning (Finn et al., 2017, Snell et al., 2017) or standard pretraining (Chen et al., 2019, Tian et al., 2020b) in a supervised manner to extract transferrable knowledge to a new few-shot task. Unfortunately, these methods require many labeled meta-training samples. Acquiring a lot of labeled data is costly or even impossible in practice. Recently, several unsupervised meta-learning approaches have attempted to address this problem by constructing synthetic tasks on unlabeled meta-training data (Hsu et al., 2019, Khodadadeh et al., 2019, 2021) or meta-training on self-supervised pretrained features (Lee et al., 2021a). However, the performance of unsupervised meta-learning approaches is still far from their supervised counterparts. Empirical studies in supervised pretraining show that representation learning via grouping similar samples together (Chen et al., 2019, Dhillon et al., 2020, Laenen and Bertinetto, 2021, Tian et al., 2020b) outperforms a wide range of episodic meta-learning methods, where the definition of similar samples is given by class labels. The motivation of this study is to develop an unsupervised representation learning method by grouping unlabeled meta-training data without episodic training and close the performance gap between supervised and unsupervised few-shot learning. Contrastive self-supervised learning has shown remarkable success in learning representation from unlabeled data, which is competitive with supervised learning on multiple visual tasks (Hénaff et al., 2020, Tian et al., 2020a).

Fingerprinting-based positioning significantly improves the indoor localization performance in non-line-of-sight-dominated areas. However, its deployment and maintenance is cost-intensive as it needs ground-truth reference systems for both the initial training and the adaption to environmental changes. In contrast, channel charting (CC) works without explicit reference information and only requires the spatial correlations of channel state information (CSI). While CC has shown promising results in modelling the geometry of the radio environment, a deeper insight into CC for localization using multi-anchor large-bandwidth measurements is still pending. We contribute a novel distance metric for time-synchronized single-input/single-output CSIs that approaches a linear correlation to the Euclidean distance. This allows to learn the environment's global geometry without annotations. To efficiently optimize the global channel chart we approximate the metric with a Siamese neural network. This enables full CC-assisted fingerprinting and positioning only using a linear transformation from the chart to the real-world coordinates. We compare our approach to the state-of-the-art of CC on two different real-world data sets recorded with a 5G and UWB radio setup. Our approach outperforms others with localization accuracies of 0.69m for the UWB and 1.4m for the 5G setup. We show that CC-assisted fingerprinting enables highly accurate localization and reduces (or eliminates) the need for annotated training data.