arXiv research

DSA efficiently allocates sparsity across layers for budgeted pruning.

Abstract perspective on quadratic programming for optimal portfolio allocation.

Dynamic risk factor model improves portfolio performance in high dimensions.

Develops FGL for better portfolio allocation under common factor influence.

Develops a new method for statistical optimal allocation problems.

In this paper, we provide a representation theorem for dynamic capital allocation under It{ô}-L{é}vy model. We consider the representation of dynamic risk measures defined under Backward Stochastic Differential Equations (BSDE) with generators that grow quadratic-exponentially in the control variables. Dynamic capital …

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy o…

Proposes a flexible feature allocation model for sparse factor analysis.

A new method for differentiable structured sparsity improves neural network performance and sparsity.

The paper tackles one-for-many counterfactual explanations using column generation.

New memory allocation scheme improves image generation performance.

In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter sparsity directly and is invariant to the scaling of parameter values, but it cannot provide useful gradi…

Embeds sparsity in deep neural networks, allowing exact zero parameters.

Register allocation, which is a crucial phase of a good optimizing compiler, relies on graph coloring. Hence, an efficient graph coloring algorithm is of paramount importance. In this work we try to learn a good heuristic for coloring interference graphs that are used in the register allocation phase. We aim to handle …

Scalar dynamic risk measures for univariate positions in continuous time are commonly represented as backward stochastic differential equations. In the multivariate setting, dynamic risk measures have been defined and studied as families of set-valued functionals in the recent literature. There are two possible extensi…

A variety of machine learning tasks---e.g., matrix factorization, topic modelling, and feature allocation---can be viewed as learning the parameters of a probability distribution over bipartite graphs. Recently, a new class of models for networks, the sparse exchangeable graphs, have been introduced to resolve some imp…

The Gradient Boosting Decision Tree (GBDT) is a popular machine learning model for various tasks in recent years. In this paper, we study how to improve model accuracy of GBDT while preserving the strong guarantee of differential privacy. Sensitivity and privacy budget are two key design aspects for the effectiveness o…

Differential privacy is concerned about the prediction quality while measuring the privacy impact on individuals whose information is contained in the data. We consider differentially private risk minimization problems with regularizers that induce structured sparsity. These regularizers are known to be convex but they…

We establish $L^{\infty}$ and $L^2$ error bounds for functions of many variables that are approximated by linear combinations of ReLU (rectified linear unit) and squared ReLU ridge functions with $\ell^1$ and $\ell^0$ controls on their inner and outer parameters. With the squared ReLU ridge function, we show th…

NMF with specific constraints is equivalent to LDA.

Proposes an efficient method for sparse index tracking with $\ell_0$-norm constraints.

New algorithm solves online resource allocation problems efficiently.

Digital transformation boosts corporate financial asset allocation, especially short-term.

Proposes a new approach to generate sparse models from deep networks.

Onflow optimizes portfolio allocation with gradient flows, robust to transaction fees.

A new method for portfolio allocation in continuous-time markets.

Algorithm ensures privacy while strictly adhering to constraints.

New DP optimization methods for sparse gradients, improving on existing algorithms.

Portfolio management problems are often divided into two types: active and passive, where the objective is to outperform and track a preselected benchmark, respectively. Here, we formulate and solve a dynamic asset allocation problem that combines these two objectives in a unified framework. We look to maximize the exp…

Reinforcement learning for continuous-time risk-sensitive asset allocation

New loss function reduces outage probability in ML-assisted resource allocation.

Improved Frank-Wolfe algorithm speeds up training of differentially private LASSO models.

Automated PDE discovery from multiple noisy experiments.

Efficient implicit differentiation for Lasso hyperparameter optimization.

Improved fMRI analysis models enhance classification performance and select relevant brain regions.

This paper challenges the conventional wisdom of trend-following by showing that the medium-term horizon adds little value once short- and long-term components are included.

Paper develops a method to learn optimal sparsity-promoting regularizers for linear inverse problems.

Boosting as gradient descent algorithms is one popular method in machine learning. In this paper a novel Boosting-type algorithm is proposed based on restricted gradient descent with structural sparsity control whose underlying dynamics are governed by differential inclusions. In particular, we present an iterative reg…

We introduce a dynamic generative model, Bayesian allocation model (BAM), which establishes explicit connections between nonnegative tensor factorization (NTF), graphical models of discrete probability distributions and their Bayesian extensions, and the topic models such as the latent Dirichlet allocation. BAM is base…

New framework for calculating multivariate risk measures using Wishart process.

Predictive policing models can be biased by differential crime reporting rates.

In the last few years, the financial advisory industry has been impacted by the emergence of digitalization and robo-advisors. This phenomenon affects major financial services, including wealth management, employee savings plans, asset managers, etc. Since the robo-advisory model is in its early stages, we estimate tha…

PrAda-GAN improves synthetic data generation under differential privacy.

SCOPE iteratively optimizes sparsity-constrained problems without tuning hyperparameters.

To scale non-parametric extensions of probabilistic topic models such as Latent Dirichlet allocation to larger data sets, practitioners rely increasingly on parallel and distributed systems. In this work, we study data-parallel training for the hierarchical Dirichlet process (HDP) topic model. Based upon a representati…

Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discrete count data such as text and images. Applications require LDA to handle both large datasets and a large number of topics. Though distributed CPU systems have been used, GPU-based systems have emerged as a promising alternative because of the high…

The popularity of modern portfolio theory has decreased among practitioners because of its unfavorable out-of-sample performance. Estimation errors tend to affect the optimal weight calculation noticeably, especially when a large number of assets is considered. To overcome these issues, many methods have been proposed …

Developing efficient and scalable algorithms for Latent Dirichlet Allocation (LDA) is of wide interest for many applications. Previous work has developed an O(1) Metropolis-Hastings sampling method for each token. However, the performance is far from being optimal due to random accesses to the parameter matrices and fr…