We provide an efficient unified plug-in approach for estimating symmetric properties of distributions given $n$ independent samples. Our estimator is based on profile-maximum-likelihood (PML) and is sample optimal for estimating various symmetric properties when the estimation error $\epsilon \gg n^{-1/3}$. This result improves upon the previous best accuracy threshold of $\epsilon \gg n^{-1/4}$ achievable by polynomial time computable PML-based universal estimators [ACSS21, ACSS20]. Our estimator reaches a theoretical limit for universal symmetric property estimation as [Han21] shows that a broad class of universal estimators (containing many well known approaches including ours) cannot be sample optimal for every $1$-Lipschitz property when $\epsilon \ll n^{-1/3}$.
Commercial ML APIs offered by providers such as Google, Amazon and Microsoft have dramatically simplified ML adoption in many applications. Numerous companies and academics pay to use ML APIs for tasks such as object detection, OCR and sentiment analysis. Different ML APIs tackling the same task can have very heterogeneous performance. Moreover, the ML models underlying the APIs also evolve over time. As ML APIs rapidly become a valuable marketplace and a widespread way to consume machine learning, it is critical to systematically study and compare different APIs with each other and to characterize how APIs change over time. However, this topic is currently underexplored due to the lack of data. In this paper, we present HAPI (History of APIs), a longitudinal dataset of 1,761,417 instances of commercial ML API applications (involving APIs from Amazon, Google, IBM, Microsoft and other providers) across diverse tasks including image tagging, speech recognition and text mining from 2020 to 2022. Each instance consists of a query input for an API (e.g., an image or text) along with the API's output prediction/annotation and confidence scores. HAPI is the first large-scale dataset of ML API usages and is a unique resource for studying ML-as-a-service (MLaaS). As examples of the types of analyses that HAPI enables, we show that ML APIs' performance change substantially over time--several APIs' accuracies dropped on specific benchmark datasets. Even when the API's aggregate performance stays steady, its error modes can shift across different subtypes of data between 2020 and 2022. Such changes can substantially impact the entire analytics pipelines that use some ML API as a component. We further use HAPI to study commercial APIs' performance disparities across demographic subgroups over time. HAPI can stimulate more research in the growing field of MLaaS.
Transient signals are often composed of a series of modes that have multivalued time-dependent instantaneous frequency (IF), which brings challenges to the development of signal processing technology. Fortunately, the group delay (GD) of such signal can be well expressed as a single valued function of frequency. By considering the frequency-domain signal model, we present a postprocessing method called wavelet transform (WT)-based time-reassigned synchrosqueezing transform (WTSST). Our proposed method embeds a two-dimensional GD operator into a synchrosqueezing framework to generate a time-frequency representation (TFR) of transient signal with high energy concentration and allows to retrieve the whole or part of the signal. The theoretical analyses of the WTSST are provided, including the analysis of GD candidate accuracy and signal reconstruction accuracy. Moreover, based on WTSST, the WT-based time-reassigned multisynchrosqueezing transform (WTMSST) is proposed by introducing a stepwise refinement scheme, which further improves the drawback that the WTSST method is unable to deal with strong frequency-varying signal. Simulation and real signal analysis illustrate that the proposed methods have the capacity to appropriately describe the features of transient signals.
A novel cross-domain attentional multi-task architecture - xDom - for robust real-world wireless radio frequency (RF) fingerprinting is presented in this work. To the best of our knowledge, this is the first time such comprehensive attention mechanism is applied to solve RF fingerprinting problem. In this paper, we resort to real-world IoT WiFi and Bluetooth (BT) emissions (instead of synthetic waveform generation) in a rich multipath and unavoidable interference environment in an indoor experimental testbed. We show the impact of the time-frame of capture by including waveforms collected over a span of months and demonstrate the same time-frame and multiple time-frame fingerprinting evaluations. The effectiveness of resorting to a multi-task architecture is also experimentally proven by conducting single-task and multi-task model analyses. Finally, we demonstrate the significant gain in performance achieved with the proposed xDom architecture by benchmarking against a well-known state-of-the-art model for fingerprinting. Specifically, we report performance improvements by up to 59.3% and 4.91x under single-task WiFi and BT fingerprinting respectively, and up to 50.5% increase in fingerprinting accuracy under the multi-task setting.
Continuous monitoring with an ever-increasing number of sensors has become ubiquitous across many application domains. Acquired data are typically high-dimensional and difficult to interpret, but they are also hypothesized to lie on a lower-dimensional manifold. Many deep learning (DL) models aim to identify this manifold, but do not promote structure nor interpretability. We propose the SOM-CPC model, which jointly optimizes Contrastive Predictive Coding (CPC), and a Self-Organizing Map (SOM) to find such an organized manifold. We address a largely unexplored and challenging set of scenarios comprising high-rate time series, and show on synthetic and real-life medical and audio data that SOM-CPC outperforms strong baseline models that combine DL with SOMs. SOM-CPC has great potential to expose latent patterns in high-rate data streams, and may therefore contribute to a better understanding of many different processes and systems.
In this paper, a high noise immune time-domain inversion cascade network (TICaN) is proposed to reconstruct scatterers from the measured electromagnetic fields. The TICaN is comprised of a denoising block aiming at improving the signal-to-noise ratio, and an inversion block to reconstruct the electromagnetic properties from the raw time-domain measurements. The scatterers investigated in this study include complicated geometry shapes and high contrast, which cover the stratum layer, lossy medium and hyperfine structure, etc. After being well trained, the performance of the TICaN is evaluated from the perspective of accuracy, noise-immunity, computational acceleration, and generalizability. It can be proven that the proposed framework can realize high-precision inversion under high-intensity noise environments. Compared with traditional reconstruction methods, TICaN avoids the tedious iterative calculation by utilizing the parallel computing ability of GPU and thus significantly reduce the computing time. Besides, the proposed TICaN has certain generalization ability in reconstructing the unknown scatterers such as the famous Austria rings. Herein, it is confident that the proposed TICaN will serve as a new path for real-time quantitative microwave imaging for various practical scenarios.
Markov chain Monte Carlo (MCMC) methods are often used in clustering since they guarantee asymptotically exact expectations in the infinite-time limit. In finite time, though, slow mixing often leads to poor performance. Modern computing environments offer massive parallelism, but naive implementations of parallel MCMC can exhibit substantial bias. In MCMC samplers of continuous random variables, Markov chain couplings can overcome bias. But these approaches depend crucially on paired chains meetings after a small number of transitions. We show that straightforward applications of existing coupling ideas to discrete clustering variables fail to meet quickly. This failure arises from the "label-switching problem": semantically equivalent cluster relabelings impede fast meeting of coupled chains. We instead consider chains as exploring the space of partitions rather than partitions' (arbitrary) labelings. Using a metric on the partition space, we formulate a practical algorithm using optimal transport couplings. Our theory confirms our method is accurate and efficient. In experiments ranging from clustering of genes or seeds to graph colorings, we show the benefits of our coupling in the highly parallel, time-limited regime.
The fast adaptation capability of deep neural networks in non-stationary environments is critical for online time series forecasting. Successful solutions require handling changes to new and recurring patterns. However, training deep neural forecaster on the fly is notoriously challenging because of their limited ability to adapt to non-stationary environments and the catastrophic forgetting of old knowledge. In this work, inspired by the Complementary Learning Systems (CLS) theory, we propose Fast and Slow learning Networks (FSNet), a holistic framework for online time-series forecasting to simultaneously deal with abrupt changing and repeating patterns. Particularly, FSNet improves the slowly-learned backbone by dynamically balancing fast adaptation to recent changes and retrieving similar old knowledge. FSNet achieves this mechanism via an interaction between two complementary components of an adapter to monitor each layer's contribution to the lost, and an associative memory to support remembering, updating, and recalling repeating events. Extensive experiments on real and synthetic datasets validate FSNet's efficacy and robustness to both new and recurring patterns. Our code will be made publicly available.
3D Time-of-Flight (ToF) image sensors are used widely in applications such as self-driving cars, Augmented Reality (AR) and robotics. When implemented with Single-Photon Avalanche Diodes (SPADs), compact, array format sensors can be made that offer accurate depth maps over long distances, without the need for mechanical scanning. However, array sizes tend to be small, leading to low lateral resolution, which combined with low Signal-to-Noise Ratio (SNR) levels under high ambient illumination, may lead to difficulties in scene interpretation. In this paper, we use synthetic depth sequences to train a 3D Convolutional Neural Network (CNN) for denoising and upscaling (x4) depth data. Experimental results, based on synthetic as well as real ToF data, are used to demonstrate the effectiveness of the scheme. With GPU acceleration, frames are processed at >30 frames per second, making the approach suitable for low-latency imaging, as required for obstacle avoidance.
High frame rates are desired in many fields of application. As in many cases the frame repetition rate of an already captured video has to be increased, frame rate up-conversion (FRUC) is of high interest. We conduct a motion compensated approach. From two neighboring frames, the motion is estimated and the neighboring pixels are shifted along the motion vector into the frame to be reconstructed. For displaying, these irregularly distributed mesh pixels have to be resampled onto regularly spaced grid positions. We use the model-based key point agnostic frequency-selective mesh-to-grid resampling (AFSMR) for this task and show that AFSMR works best for applications that contain irregular meshes with varying densities. AFSMR gains up to 3.2 dB in contrast to the already high performing frequency-selective mesh-to-grid resampling (FSMR). Additionally, AFSMR increases the run time by a factor of 11 relative to FSMR.