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.
Optimization algorithm CoCo improves causal inference from diverse data.
Humans can only interact with part of the surrounding environment due to biological restrictions. Therefore, we learn to reason the spatial relationships across a series of observations to piece together the surrounding environment. Inspired by such behavior and the fact that machines also have computational constraint…
CoCos can increase financial fragility in certain network structures.
Contingent Convertible bonds (CoCos) are debt instruments that convert into equity or are written down in times of distress. Existing pricing models assume conversion triggers based on market prices and on the assumption that markets can always observe all relevant firm information. But all Cocos issued so far have tri…
Study compares high-dimensional BO algorithms on 24 functions.
We develop a pricing model for Sovereign Contingent Convertible bonds (S-CoCo) with payment standstills triggered by a sovereign's Credit Default Swap (CDS) spread. We model CDS spread regime switching, which is prevalent during crises, as a hidden Markov process, coupled with a mean-reverting stochastic process of spr…
We introduce COCO, an open source platform for Comparing Continuous Optimizers in a black-box setting. COCO aims at automatizing the tedious and repetitive task of benchmarking numerical optimization algorithms to the greatest possible extent. The platform and the underlying methodology allow to benchmark in the same f…
The paper examines how CoCo bonds can enhance financial stability in interconnected banking systems.
Self-training outperforms pre-training on COCO object detection and segmentation datasets.
QC-ST and CoCo methods correct batch effects in metabolomics data.
Cluster analysis is a fundamental tool for pattern discovery of complex heterogeneous data. Prevalent clustering methods mainly focus on vector or matrix-variate data and are not applicable to general-order tensors, which arise frequently in modern scientific and business applications. Moreover, there is a gap between …
Visual Human Activity Recognition (HAR) and data fusion with other sensors can help us at tracking the behavior and activity of underground miners with little obstruction. Existing models, such as Single Shot Detector (SSD), trained on the Common Objects in Context (COCO) dataset is used in this paper to detect the cur…
After the beginning of the credit and liquidity crisis, financial institutions have been considering creating a convertible-bond type contract focusing on Capital. Under the terms of this contract, a bond is converted into equity if the authorities deem the institution to be under-capitalized. This paper discusses this…
In this paper we analyze an extension of the Jeanblanc and Valchev (2005) model by considering a short-term uncertainty model with two noises. It is a combination of the ideas of Duffie and Lando (2001) and Jeanblanc and Valchev (2005): share quotations of the firm are available at the financial market, and these can b…
Proposes group whitening to enhance deep learning models' performance.
Optimal bounds on regret and constraint violation in adversarial COCO.
This study evaluates Bayesian optimization algorithms on a wide range of problems.
Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first …
EGL optimizes complex functions without fitting them, achieving state-of-the-art results.
We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries. An existing method concatenated $\X$ and $\Y$ as $[\X; \Y]$ and applied a matrix completion (MC) method to fill the missing entries, under the assumption that $[\X; \Y]$ is of low-rank…
We propose , a novel self-regularized non-monotonic activation function which can be mathematically defined as: . As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks…
Improved COCO algorithms with better constraint control.
Paper presents attacks on real-time object detection systems.
Paper introduces MCSD, a method for uncertainty estimation in deep learning.
The backpropagation (BP) algorithm is often thought to be biologically implausible in the brain. One of the main reasons is that BP requires symmetric weight matrices in the feedforward and feedback pathways. To address this "weight transport problem" (Grossberg, 1987), two more biologically plausible algorithms, propo…
The Monte Carlo pathwise sensitivities approach is well established for smooth payoff functions. In this work, we present a new Monte Carlo algorithm that is able to calculate the pathwise sensitivities for discontinuous payoff functions. Our main tool is to combine the one-step survival idea of Glasserman and Staum wi…
Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent t…
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator learns to model label dependency by discriminating real and generated label set…
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over…
We propose a simple technique for encouraging generative RNNs to plan ahead. We train a "backward" recurrent network to generate a given sequence in reverse order, and we encourage states of the forward model to predict cotemporal states of the backward model. The backward network is used only during training, and play…
Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained cheaply. The problem is formulated using an undirected graphical model that represe…
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficie…
We introduce here for the first time the long-term swap rate, characterised as the fair rate of an overnight indexed swap with infinitely many exchanges. Furthermore we analyse the relationship between the long-term swap rate, the long-term yield, see Biagini et al. [2018], Biagini and Härtel [2014], and El Karoui et a…
Paper improves COCO problem, reducing constraint violation at the cost of slightly more regret.
Low level features like edges and textures play an important role in accurately localizing instances in neural networks. In this paper, we propose an architecture which improves feature pyramid networks commonly used instance segmentation networks by incorporating low level features in all layers of the pyramid in an o…
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets,…
In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is sufficiently rich, the SI method is a useful learning algorithm. In particular, we show that larger data imbalance, a quality that is typically per…
We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this transform preserves most of the signal information nee…
AECF improves multimodal inference robustness and calibration.
We present a new data-driven benchmark system to evaluate the performance of new MCMC samplers. Taking inspiration from the COCO benchmark in optimization, we view this task as having critical importance to machine learning and statistics given the rate at which new samplers are proposed. The common hand-crafted exampl…
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn stylistic and stochastic modifications leveraging state-of-the-art generative models. …
Predicting not only the target but also an accurate measure of uncertainty is important for many machine learning applications and in particular safety-critical ones. In this work we study the calibration of uncertainty prediction for regression tasks which often arise in real-world systems. We show that the existing d…
Enhanced rotation prediction improves SSL models by capturing both shape and texture information.
Model learns image-word associations from captions using contrastive learning.
Efficient search methods can outperform random search on challenging tasks.
ViCE uses superpixels to enhance self-supervised learning for better dense visual embeddings.
Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of tuning. We present a single model that yields good results on a number of problems sp…
Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the unde…