arXiv research

This paper is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We assume no math knowledge beyond what you learned in calculus 1, and provide links to help you refresh the necessary math where needed. Note that you do not need to understand this materia…

Investigates optimal pension policies in PAYG systems with forward utility and ageing population.

This research presents an analysis of the demographic risk related to future membership patterns in pension funds with restricted entrance, financed under a pay-as-you-go scheme. The paper, therefore, proposes a stochastic model for investigating the behaviour of the demographic variable "new entrants" and the influenc…

In this report, we talked about a new quantitative strategy for choosing the optimal(s) stock(s) to trade. The basic notions are generally very known by the financial community. The key here is to understand 1) the standard score applied to a sample and 2) the correlation factor applied to different time series in real…

The paper optimizes pension policies with guarantees and sustainability constraints.

Develops a new trend power indicator using DSP techniques.

Optimization learns as it goes, improving with experience.

Despite the widespread usage of machine learning throughout organizations, there are some key principles that are commonly missed. In particular: 1) There are at least four main families for supervised learning: logical modeling methods, linear combination methods, case-based reasoning methods, and iterative summarizat…

New DP training ensures models behave similarly at training and test time.

Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this infer…

DeeperGCN tackles deep GCNs by overcoming vanishing gradient and over-smoothing issues.

As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assura…

FedBE aggregates local models into a robust global model via Bayesian inference.

This paper proposes a unified framework for recognizing seen and unseen classes using visual and semantic prototypes.

Solves a problem about deforming symplectic forms on a Klein bottle.

A new memory-efficient Adam variant reduces second moments when feasible.

New models ensure monotonicity in preference learning, improving accuracy especially with limited data.

Quant firms manipulate stock markets overnight and intraday.

Proposes a mixed pension system combining PAYG and funded contributions to address sustainability.

If you want to tell people the truth, make them laugh, otherwise they'll kill you. (source unclear) Machine learning and deep learning are the technologies of the day for developing intelligent automatic systems. However, a key hurdle for progress in the field is the literature itself: we often encounter papers that re…

Probabilistic models can handle causal inference without special tools.

Silence on suspicious stock market patterns persists despite lack of plausible explanations.

Study shows surfaces sound the same everywhere if they have a transitive isometry group.

The paper introduces a new insurance pricing model based on driving mileage.

We consider two well known constructions of link invariants. One uses skein theory: you resolve each crossing of the link as a linear combination of things that don't cross, until you eventually get a linear combination of links with no crossings, which you turn into a polynomial. The other uses quantum groups: you con…

The abstract discusses parallels between Galois theory and Stone-Weierstrass theorem in various fields.

Optimizes CNN architectures by analyzing receptive fields without training.

In this small article one compromise monetization strategy is proposed, which hopefully may lead to a more satisfactory coexistence of IP manufacturers and consumers. The motto is "fair exchange": you use our IP-product, we use your product (in form of money); when you do not need our product any more, we change back.

Lecture notes on geodesics in differential geometry.

We construct a pair of transverse genuine laminations on an atoroidal 3-manifold admitting transversely orientable uniform 1-cochain. The laminations are induced by the uniform 1-cochain and they are indeed the "straightening" of the coarse laminations defined in [Ca], by using minimal surface techniques. Moreover, whe…

A new method to value IPOed companies.

We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.

The paper explores the limits of tight PAC-Bayes bounds for cheap models in robust statistics.

People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately. Many techniques have been devised …

We prove a structure theorem for 3-manifolds with non-trivial JSJ-decomposition and 2-generated fundamental group. We deduce a variety of Corollaries. Note this is not a complete classification of such manifolds. In particular we believe that one of the families in our list is empty. If you know something about hyperbo…

Take a torus with a Riemannian metric. Lift the metric on its universal cover. You get a distance which in turn yields balls. On these balls you can look at the Laplacian. Focus on the spectrum for the Dirichlet or Neumann problem. We describe the asymptotic behaviour of the eigenvalues as the radius of the balls goes …

Riemannian metric learning improves data representation across various fields.

Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results.…

A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, whic…

What would you do if you were invited to play a game where you were given \$25 and allowed to place bets for 30 minutes on a coin that you were told was biased to come up heads 60% of the time? This is exactly what we did, gathering 61 young, quantitatively trained men and women to play this game. The results, in a nut…

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a …

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…

Optimizes pension mix of PAYGO, EET, and individual savings.

By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carl…

We applied machine learning to predict whether a gene is involved in axon regeneration. We extracted 31 features from different databases and trained five machine learning models. Our optimal model, a Random Forest Classifier with 50 submodels, yielded a test score of 85.71%, which is 4.1% higher than the baseline scor…

MuZero learns models to master complex games without domain knowledge.

Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most existing methods either (i) suffer from high variance, seeking help from (often) complicated variance-…

Have you ever looked at a machine learning classification model and thought, I could have made that? Well, that is what we test in this project, comparing XGBoost trained on human engineered features to training directly on data. The human engineered features do not outperform XGBoost trained di- rectly on the data, bu…