A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A new deep learning method for energy disaggregation.
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we…
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networ…
Stuttering is a speech impediment affecting tens of millions of people on an everyday basis. Even with its commonality, there is minimal data and research on the identification and classification of stuttered speech. This paper tackles the problem of detection and classification of different forms of stutter. As oppose…
RDL-Net improves speech enhancement with fewer parameters and better performance.
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the recent success of dilated convolutions in sequence modeling applications, allowin…
Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements are stacked RNNs, which increases the capacity for learning non-linear functions, and bidirectional processing, which exploits acausal informa…
Bidirectional VAE reduces parameters and improves image tasks.
Vanilla convolutional neural networks are known to provide superior performance not only in image recognition tasks but also in natural language processing and time series analysis. One of the strengths of convolutional layers is the ability to learn features about spatial relations in the input domain using various pa…
Sharp error bounds derived for bidirectional GANs without restrictive assumptions.
We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolut…
Multivariate time series classification is a high value and well-known problem in machine learning community. Feature extraction is a main step in classification tasks. Traditional approaches employ hand-crafted features for classification while convolutional neural networks (CNN) are able to extract features automatic…
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic feature…
Bidirectional LSTM predicts seizures with 84% accuracy.
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans. However, the size of a nodule is very diverse and can range anywhere between 3 and 30 millimeters. The high variation of nodule sizes makes classifying them a difficult and cha…
Paper proposes using LSTM for LSH-based sequence alignment.
This paper addresses the problem of time series forecasting for non-stationary signals and multiple future steps prediction. To handle this challenging task, we introduce DILATE (DIstortion Loss including shApe and TimE), a new objective function for training deep neural networks. DILATE aims at accurately predicting s…
We consider the task of detecting regulatory elements in the human genome directly from raw DNA. Past work has focused on small snippets of DNA, making it difficult to model long-distance dependencies that arise from DNA's 3-dimensional conformation. In order to study long-distance dependencies, we develop and release …
Bidirectional bounds stabilize training of energy-based models.
We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we ext…
The study of which mapping class group elements can be realized as affine automorphisms of dilation surfaces.
We find the minimum dilatation of pseudo-Anosov braids with many strands.
Decoding language representations directly from the brain can enable new Brain-Computer Interfaces (BCI) for high bandwidth human-human and human-machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. In this study, we prop…
Closed geodesics densely cover a circle in dilation surfaces.
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora…
Improved traffic forecasting model handles missing data.
The dilatation of a pseudo-Anosov braid is a conjugacy invariant. In this paper, we study the dilatation of a special family of pseudo-Anosov braids. We prove an inductive formula to compute their dilatation, a monotonicity and an asymptotic behavior of the dilatation for this family of braids. We also give an example …
A fundamental problem in geophysical modeling is related to the identification and approximation of causal structures among physical processes. However, resolving the bidirectional mappings between physical parameters and model state variables (i.e., solving the forward and inverse problems) is challenging, especially …
This paper describes a family of pseudo-Anosov braids with small dilatation. The smallest dilatations occurring for braids with 3, 4 and 5 strands appear in this family. A pseudo-Anosov braid with 2g+1 strands determines a hyperelliptic mapping class with the same dilatation on a genus-g surface. Penner showed that log…
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that summarize the past and future around an instance, we propose a novel architecture …
Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. This has recently been remedied with the introduction of a plug-in relational module that considers relations between pairs of objects. Unfortunately, this is combinatorially expensive. In this extended abst…
Hybrid model combines LSTM and ETS for mid-term electric load forecasting.
Horizon saddle connections imply dense hyperbolic geodesics on dilation surfaces.
Paper introduces r-DEP classifier for binary classification tasks.
For any nonorientable closed surface, we determine the minimal dilatation among pseudo-Anosov mapping classes arising from Penner's construction. We deduce that the sequence of minimal Penner dilatations has exactly two accumulation points, in contrast to the case of orientable surfaces where there is only one accumula…
In this paper we study the minimum dilatation pseudo-Anosov mapping classes coming from fibrations over the circle of a single 3-manifold, the mapping torus for the "simplest pseudo-Anosov braid". The dilatations that arise include the minimum dilatations for orientable mapping classes for genus g=2,3,4,5,8 as well as …
New theory explains signal propagation in normalization-free transformers.
We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs. First, we enforce that the empirical distribution of the inverse inference network matches the prior distribution, which favors the generator network reproducibility on the se…
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
The paper explores inequalities for strongly-convex sets in weighted Riemannian manifolds.
Maximal dilatation found on nonorientable surfaces.
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples () conditioned on both latent variables () and known auxiliary information (). We propose the Bidirectional cGAN (BiCoGAN), which effectively disentangles and in the generation process and provides a…
Constructs moduli spaces for complex affine and dilation surfaces.
A deep learning model, named IITNet, is proposed to learn intra- and inter-epoch temporal contexts from raw single-channel EEG for automatic sleep scoring. To classify the sleep stage from half-minute EEG, called an epoch, sleep experts investigate sleep-related events and consider the transition rules between the foun…
Based on the notion of dilatation structure arXiv:math/0608536, we give an intrinsic treatment to sub-riemannian geometry, started in the paper arXiv:0706.3644 . Here we prove that regular sub-riemannian manifolds admit dilatation structures. From the existence of normal frames proved by Bellaiche we deduce the rest of…
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and d…
New hybrid model predicts carbon prices using blockchain data.