Distilling analytical models from data has the potential to advance our understanding and prediction of nonlinear dynamics. Although discovery of governing equations based on observed system states (e.g., trajectory time series) has revealed success in a wide range of nonlinear dynamics, uncovering the closed-form equations directly from raw videos still remains an open challenge. To this end, we introduce a novel end-to-end unsupervised deep learning framework to uncover the mathematical structure of equations that governs the dynamics of moving objects in videos. Such an architecture consists of (1) an encoder-decoder network that learns low-dimensional spatial/pixel coordinates of the moving object, (2) a learnable Spatial-Physical Transformation component that creates mapping between the extracted spatial/pixel coordinates and the latent physical states of dynamics, and (3) a numerical integrator-based sparse regression module that uncovers the parsimonious closed-form governing equations of learned physical states and, meanwhile, serves as a constraint to the autoencoder. The efficacy of the proposed method is demonstrated by uncovering the governing equations of a variety of nonlinear dynamical systems depicted by moving objects in videos. The resulting computational framework enables discovery of parsimonious interpretable model in a flexible and accessible sensing environment where only videos are available.
Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient reasoning on long sequences with limited storage resources, memory augmented neural networks introduce a human-like write-read memory to compress and memorize the long input sequence in one pass, trying to answer subsequent queries only based on the memory. But they have two serious drawbacks: 1) they continually update the memory from current information and inevitably forget the early contents; 2) they do not distinguish what information is important and treat all contents equally. In this paper, we propose the Rehearsal Memory (RM) to enhance long-sequence memorization by self-supervised rehearsal with a history sampler. To alleviate the gradual forgetting of early information, we design self-supervised rehearsal training with recollection and familiarity tasks. Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information. We evaluate the performance of our rehearsal memory by the synthetic bAbI task and several downstream tasks, including text/video question answering and recommendation on long sequences.
We introduce a novel geometry-oriented methodology, based on the emerging tools of topological data analysis, into the change point detection framework. The key rationale is that change points are likely to be associated with changes in geometry behind the data generating process. While the applications of topological data analysis to change point detection are potentially very broad, in this paper we primarily focus on integrating topological concepts with the existing nonparametric methods for change point detection. In particular, the proposed new geometry-oriented approach aims to enhance detection accuracy of distributional regime shift locations. Our simulation studies suggest that integration of topological data analysis with some existing algorithms for change point detection leads to consistently more accurate detection results. We illustrate our new methodology in application to the two closely related environmental time series datasets -ice phenology of the Lake Baikal and the North Atlantic Oscillation indices, in a research query for a possible association between their estimated regime shift locations.
First-price auctions have largely replaced traditional bidding approaches based on Vickrey auctions in programmatic advertising. As far as learning is concerned, first-price auctions are more challenging because the optimal bidding strategy does not only depend on the value of the item but also requires some knowledge of the other bids. They have already given rise to several works in sequential learning, many of which consider models for which the value of the buyer or the opponents' maximal bid is chosen in an adversarial manner. Even in the simplest settings, this gives rise to algorithms whose regret grows as $\sqrt{T}$ with respect to the time horizon $T$. Focusing on the case where the buyer plays against a stationary stochastic environment, we show how to achieve significantly lower regret: when the opponents' maximal bid distribution is known we provide an algorithm whose regret can be as low as $\log^2(T)$; in the case where the distribution must be learnt sequentially, a generalization of this algorithm can achieve $T^{1/3+ \epsilon}$ regret, for any $\epsilon>0$. To obtain these results, we introduce two novel ideas that can be of interest in their own right. First, by transposing results obtained in the posted price setting, we provide conditions under which the first-price biding utility is locally quadratic around its optimum. Second, we leverage the observation that, on small sub-intervals, the concentration of the variations of the empirical distribution function may be controlled more accurately than by using the classical Dvoretzky-Kiefer-Wolfowitz inequality. Numerical simulations confirm that our algorithms converge much faster than alternatives proposed in the literature for various bid distributions, including for bids collected on an actual programmatic advertising platform.
Federated learning enables model training over a distributed corpus of agent data. However, the trained model is vulnerable to adversarial examples, designed to elicit misclassification. We study the feasibility of using adversarial training (AT) in the federated learning setting. Furthermore, we do so assuming a fixed communication budget and non-iid data distribution between participating agents. We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training. We attribute this to the number of epochs of AT performed locally at the agents, which in turn effects (i) drift between local models; and (ii) convergence time (measured in number of communication rounds). Towards this end, we propose FedDynAT, a novel algorithm for performing AT in federated setting. Through extensive experimentation we show that FedDynAT significantly improves both natural and adversarial accuracy, as well as model convergence time by reducing the model drift.
Sounds recorded with smartphones or IoT devices often have partially unreliable observations caused by clipping, wind noise, and completely missing parts due to microphone failure and packet loss in data transmission over the network. In this paper, we investigate the impact of the partially missing channels on the performance of acoustic scene classification using multichannel audio recordings, especially for a distributed microphone array. Missing observations cause not only losses of time-frequency and spatial information on sound sources but also a mismatch between a trained model and evaluation data. We thus investigate how a missing channel affects the performance of acoustic scene classification in detail. We also propose simple data augmentation methods for scene classification using multichannel observations with partially missing channels and evaluate the scene classification performance using the data augmentation methods.
Currently there has been increasing demand for real-time training on resource-limited IoT devices such as smart sensors, which realizes standalone online adaptation for streaming data without data transfers to remote servers. OS-ELM (Online Sequential Extreme Learning Machine) has been one of promising neural-network-based online algorithms for on-chip learning because it can perform online training at low computational cost and is easy to implement as a digital circuit. Existing OS-ELM digital circuits employ fixed-point data format and the bit-widths are often manually tuned, however, this may cause overflow or underflow which can lead to unexpected behavior of the circuit. For on-chip learning systems, an overflow/underflow-free design has a great impact since online training is continuously performed and the intervals of intermediate variables will dynamically change as time goes by. In this paper, we propose an overflow/underflow-free bit-width optimization method for fixed-point digital circuit of OS-ELM. Experimental results show that our method realizes overflow/underflow-free OS-ELM digital circuits with 1.0x - 1.5x more area cost compared to an ordinary simulation-based optimization method where overflow or underflow can happen.
In academia, the research performance of a faculty is either evaluated by the number of publications or the number of citations. Most of the time h-index is widely used during the hiring process or the faculty performance evaluation. The calculation of the h-index is shown in various databases; however, there is no systematic evidence about the differences between them. Here we analyze the publication records of 385 authors from Monash University (Australia) to investigate (i) the impact of different databases like Scopus and WoS on the ranking of authors within a discipline, and (ii) to complement the $h$-index, named $h_c$, by adding the weight of the highest cited paper to the $h$-index of the authors. The results show the positive impact of $h_c$ on the lower-ranked authors in every discipline. Also, Scopus provides an overall better ranking than WoS; however, the ranking varies among Scopus and WoS for disciplines.
Bilevel optimization recently has attracted increased interest in machine learning due to its many applications such as hyper-parameter optimization and policy optimization. Although some methods recently have been proposed to solve the bilevel problems, these methods do not consider using adaptive learning rates. To fill this gap, in the paper, we propose a class of fast and effective adaptive methods for solving bilevel optimization problems that the outer problem is possibly nonconvex and the inner problem is strongly-convex. Specifically, we propose a fast single-loop BiAdam algorithm based on the basic momentum technique, which achieves a sample complexity of $\tilde{O}(\epsilon^{-4})$ for finding an $\epsilon$-stationary point. At the same time, we propose an accelerated version of BiAdam algorithm (VR-BiAdam) by using variance reduced technique, which reaches the best known sample complexity of $\tilde{O}(\epsilon^{-3})$. To further reduce computation in estimating derivatives, we propose a fast single-loop stochastic approximated BiAdam algorithm (saBiAdam) by avoiding the Hessian inverse, which still achieves a sample complexity of $\tilde{O}(\epsilon^{-4})$ without large batches. We further present an accelerated version of saBiAdam algorithm (VR-saBiAdam), which also reaches the best known sample complexity of $\tilde{O}(\epsilon^{-3})$. We apply the unified adaptive matrices to our methods as the SUPER-ADAM \citep{huang2021super}, which including many types of adaptive learning rates. Moreover, our framework can flexibly use the momentum and variance reduced techniques. In particular, we provide a useful convergence analysis framework for both the constrained and unconstrained bilevel optimization. To the best of our knowledge, we first study the adaptive bilevel optimization methods with adaptive learning rates.
End-to-end spoken language understanding (SLU) has recently attracted increasing interest. Compared to the conventional tandem-based approach that combines speech recognition and language understanding as separate modules, the new approach extracts users' intentions directly from the speech signals, resulting in joint optimization and low latency. Such an approach, however, is typically designed to process one intention at a time, which leads users to take multiple rounds to fulfill their requirements while interacting with a dialogue system. In this paper, we propose a streaming end-to-end framework that can process multiple intentions in an online and incremental way. The backbone of our framework is a unidirectional RNN trained with the connectionist temporal classification (CTC) criterion. By this design, an intention can be identified when sufficient evidence has been accumulated, and multiple intentions can be identified sequentially. We evaluate our solution on the Fluent Speech Commands (FSC) dataset and the intent detection accuracy is about 97 % on all multi-intent settings. This result is comparable to the performance of the state-of-the-art non-streaming models, but is achieved in an online and incremental way. We also employ our model to a keyword spotting task using the Google Speech Commands dataset and the results are also highly promising.