Local Differential Privacy for Sequential Decision Making in a Changing Environment

We study the problem of preserving privacy while still providing high utility in sequential decision making scenarios in a changing environment. We consider abruptly changing environment: the environment remains constant during periods and it changes at unknown time instants. To formulate this problem, we propose a variant of multi-armed bandits called non-stationary stochastic corrupt bandits. We construct an algorithm called SW-KLUCB-CF and prove an upper bound on its utility using the performance measure of regret. The proven regret upper bound for SW-KLUCB-CF is near-optimal in the number of time steps and matches the best known bound for analogous problems in terms of the number of time steps and the number of changes. Moreover, we present a provably optimal mechanism which can guarantee the desired level of local differential privacy while providing high utility.

Deep learning enhanced noise spectroscopy of a spin qubit environment

The undesired interaction of a quantum system with its environment generally leads to a coherence decay of superposition states in time. A precise knowledge of the spectral content of the noise induced by the environment is crucial to protect qubit coherence and optimize its employment in quantum device applications. We experimentally show that the use of neural networks can highly increase the accuracy of noise spectroscopy, by reconstructing the power spectral density that characterizes an ensemble of carbon impurities around a nitrogen-vacancy (NV) center in diamond. Neural networks are trained over spin coherence functions of the NV center subjected to different Carr-Purcell sequences, typically used for dynamical decoupling (DD). As a result, we determine that deep learning models can be more accurate than standard DD noise-spectroscopy techniques, by requiring at the same time a much smaller number of DD sequences.

Real-time Caller Intent Detection In Human-Human Customer Support Spoken Conversations

Agent assistance during human-human customer support spoken interactions requires triggering workflows based on the caller's intent (reason for call). Timeliness of prediction is essential for a good user experience. The goal is for a system to detect the caller's intent at the time the agent would have been able to detect it (Intent Boundary). Some approaches focus on predicting the output offline, i.e. once the full spoken input (e.g. the whole conversational turn) has been processed by the ASR system. This introduces an undesirable latency in the prediction each time the intent could have been detected earlier in the turn. Recent work on voice assistants has used incremental real-time predictions at a word-by-word level to detect intent before the end of a command. Human-directed and machine-directed speech however have very different characteristics. In this work, we propose to apply a method developed in the context of voice-assistant to the problem of online real time caller's intent detection in human-human spoken interactions. We use a dual architecture in which two LSTMs are jointly trained: one predicting the Intent Boundary (IB) and then other predicting the intent class at the IB. We conduct our experiments on our private dataset comprising transcripts of human-human telephone conversations from the telecom customer support domain. We report results analyzing both the accuracy of our system as well as the impact of different architectures on the trade off between overall accuracy and prediction latency.

Synthetic Wavelength Imaging -- Utilizing Spectral Correlations for High-Precision Time-of-Flight Sensing

This book chapter describes how spectral correlations in scattered light fields can be utilized for high-precision time-of-flight sensing. The chapter should serve as a gentle introduction and is intended for computational imaging scientists and students new to the fascinating topic of synthetic wavelength imaging. Technical details (such as detector or light source specifications) will be largely omitted. Instead, the similarities between different methods will be emphasized to "draw the bigger picture."

Post-Train Adaptive U-Net for Image Segmentation

Typical neural network architectures used for image segmentation cannot be changed without further training. This is quite limiting as the network might not only be executed on a powerful server, but also on a mobile or edge device. Adaptive neural networks offer a solution to the problem by allowing certain adaptivity after the training process is complete. In this work for the first time, we apply Post-Train Adaptive (PTA) approach to the task of image segmentation. We introduce U-Net+PTA neural network, which can be trained once, and then adapted to different device performance categories. The two key components of the approach are PTA blocks and PTA-sampling training strategy. The post-train configuration can be done at runtime on any inference device including mobile. Also, the PTA approach has allowed to improve image segmentation Dice score on the CamVid dataset. The final trained model can be switched at runtime between 6 PTA configurations, which differ by inference time and quality. Importantly, all of the configurations have better quality than the original U-Net (No PTA) model.

LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud

LiDARs have been widely adopted to modern self-driving vehicles, providing 3D information of the scene and surrounding objects. However, adverser weather conditions still pose significant challenges to LiDARs since point clouds captured during snowfall can easily be corrupted. The resulting noisy point clouds degrade downstream tasks such as mapping. Existing works in de-noising point clouds corrupted by snow are based on nearest-neighbor search, and thus do not scale well with modern LiDARs which usually capture $100k$ or more points at 10Hz. In this paper, we introduce an unsupervised de-noising algorithm, LiSnowNet, running 52$\times$ faster than the state-of-the-art methods while achieving superior performance in de-noising. Unlike previous methods, the proposed algorithm is based on a deep convolutional neural network and can be easily deployed to hardware accelerators such as GPUs. In addition, we demonstrate how to use the proposed method for mapping even with corrupted point clouds.

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

In this paper, targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we propose a new task, disentanglement of diffusion probabilistic models (DPMs), to take advantage of the remarkable modeling ability of DPMs. To tackle this task, we further devise an unsupervised approach named DisDiff. For the first time, we achieve disentangled representation learning in the framework of diffusion probabilistic models. Given a pre-trained DPM, DisDiff can automatically discover the inherent factors behind the image data and disentangle the gradient fields of DPM into sub-gradient fields, each conditioned on the representation of each discovered factor. We propose a novel Disentangling Loss for DisDiff to facilitate the disentanglement of the representation and sub-gradients. The extensive experiments on synthetic and real-world datasets demonstrate the effectiveness of DisDiff.

Improved Text Classification via Test-Time Augmentation

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.

A Log-Linear Non-Parametric Online Changepoint Detection Algorithm based on Functional Pruning

Online changepoint detection aims to detect anomalies and changes in real-time in high-frequency data streams, sometimes with limited available computational resources. This is an important task that is rooted in many real-world applications, including and not limited to cybersecurity, medicine and astrophysics. While fast and efficient online algorithms have been recently introduced, these rely on parametric assumptions which are often violated in practical applications. Motivated by data streams from the telecommunications sector, we build a flexible nonparametric approach to detect a change in the distribution of a sequence. Our procedure, NP-FOCuS, builds a sequential likelihood ratio test for a change in a set of points of the empirical cumulative density function of our data. This is achieved by keeping track of the number of observations above or below those points. Thanks to functional pruning ideas, NP-FOCuS has a computational cost that is log-linear in the number of observations and is suitable for high-frequency data streams. In terms of detection power, NP-FOCuS is seen to outperform current nonparametric online changepoint techniques in a variety of settings. We demonstrate the utility of the procedure on both simulated and real data.

Stochastic Gradient Descent-induced drift of representation in a two-layer neural network

Representational drift refers to over-time changes in neural activation accompanied by a stable task performance. Despite being observed in the brain and in artificial networks, the mechanisms of drift and its implications are not fully understood. Motivated by recent experimental findings of stimulus-dependent drift in the piriform cortex, we use theory and simulations to study this phenomenon in a two-layer linear feedforward network. Specifically, in a continual learning scenario, we study the drift induced by the noise inherent in the Stochastic Gradient Descent (SGD). By decomposing the learning dynamics into the normal and tangent spaces of the minimum-loss manifold, we show the former correspond to a finite variance fluctuation, while the latter could be considered as an effective diffusion process on the manifold. We analytically compute the fluctuation and the diffusion coefficients for the stimuli representations in the hidden layer as a function of network parameters and input distribution. Further, consistent with experiments, we show that the drift rate is slower for a more frequently presented stimulus. Overall, our analysis yields a theoretical framework for better understanding of the drift phenomenon in biological and artificial neural networks.