RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
problem Efficiently learning rhythmic motion in reinforcement learning.
method Combining RNNs and SCN structures to create RCNs.
result RCNs outperform MLPs and SCNs across all environment tasks.
Smart Close-out Netting aims to automate close-out netting processes.
problem Inefficiencies in close-out netting processes for financial institutions.
method Standardisation and automation of legal and regulatory processes using a data-driven framework and controlled natural language.
result Standardisation and automation can improve close-out netting processes for prudentially regulated financial institutions.
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.
problem Uncertainty quantification in deep neural networks.
method Viewing DNN transformations as state evolution of a stochastic dynamical system, introducing a Brownian motion term for epistemic uncertainty.
result SDE-Net outperforms existing methods in uncertainty estimation across various tasks.
We pose an optimal control problem arising in a perhaps new model for retirement investing. Given a control function f and our current net worth as X(t) for any t, we invest an amount f(X(t)) in the market. We need a fortune of M "superdollars" to retire and want to retire as early as possible. We model our c…
SymODEN learns physical systems dynamics from data.
problem Learning dynamics of physical systems from limited data.
method Physics-informed deep learning with Hamiltonian dynamics and control.
result SymODEN generalizes well with fewer samples and interpretable models.
Mean-field neural nets approximate functions using a free energy functional and controlled dynamics.
problem Function approximation by two-layer neural nets in the mean-field regime.
method Phrasing function approximation as global minimization of a free energy functional, examining dynamics in the space of probability measures over weights.
result Characterization of the unique global minimizer and dynamics achieving it, including the Föllmer drift.
We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an ℓ1-regularizer for inducing the sparsity and an ℓ2-regularizer for controlling the smoothness. We focus on a sparse setting where the total number of kernels is large but the number of non…
A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforwa…
NCDEs improve predictions for irregular time series data.
problem Theoretical understanding of NCDEs' performance and irregular time series effects.
method Combining CDE theory and neural net complexity measures.
result Generalization bound and detailed sampling and approximation bias analysis.
We investigate the learning rate of multiple kernel learning (MKL) with ℓ1 and elastic-net regularizations. The elastic-net regularization is a composition of an ℓ1-regularizer for inducing the sparsity and an ℓ2-regularizer for controlling the smoothness. We focus on a sparse setting where the total …
Optimizes gradual reduction of excess carbon emissions to net-zero.
problem Achieving net-zero carbon emissions through gradual reduction of excess emissions.
method Stochastic control approach to identify optimal emission strategy under constraints.
result Identifies the emission strategy that maximizes future profit from excess emissions.
Novel bistable structures made from four-bar linkages, proving existence and construction.
problem Existence and construction of bistable mechanical structures composed of four-bar linkages.
method Geometric construction starting from infinitesimally flexible quad nets, applying Whiteley de-averaging.
result Construction of bistable structures from well-known quad nets, allowing control of geometric parameters.
We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1 regularization (inducing sparse kernel combination), block-l2 regularization (inducing un…
RMT-Net tackles biased credit scoring data by learning from both default/non-default and rejection/approval tasks.
problem Missing-not-at-random selection bias in financial credit scoring data.
method Reject-aware Multi-Task Network (RMT-Net) that leverages the correlation between default/non-default and rejection/approval tasks.
result RMT-Net improves credit scoring models by learning from both default/non-default and rejection/approval tasks.
Deep neural nets approximate high-dimensional HJB equations efficiently.
problem Approximating solutions to high-dimensional HJB equations.
method Deep neural networks for approximating solutions.
result Deep neural networks can approximate solutions without the curse of dimensionality.
EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.
problem Limited use of neural networks in high-dimensional data with small samples.
method Ensemble by Averaging Sparse-Input Hierarchical networks (EASIER-net) with small modifications to neural network architecture and training procedure.
result EASIER-net achieves higher prediction accuracy than off-the-shelf methods on average.
Neural ODEs simplified using Chen-Fliess series for Rademacher complexity analysis.
problem Analyzing the complexity of neural ODE models.
method Using Chen-Fliess series to frame neural ODEs as infinite-width nets, where weights are signature of control input and features are Lie derivatives.
result Derived compact expressions for the Rademacher complexity of ODE models.
New method uses neural nets to control systems safely with disturbances.
problem Designing safe control laws for systems with disturbances.
method Imitation learning to train neural network controllers that satisfy CBF constraints.
result Demonstrated on a unicycle model with external disturbances.
APAC-Net solves high-dimensional stochastic MFGs using neural networks.
problem High-dimensional stochastic mean-field games.
method Alternating population and control neural networks, parameterizing value and density functions.
result Solves up to 100-dimensional MFG problems.
IEN speeds up T-Rex+GVS for fast, efficient GWAS.
problem Efficiently selecting groups of genetic variants in large-scale genomics studies.
method Informed Elastic Net (IEN) as a faster base selector for T-Rex+GVS.
result IEN reduces computation time while maintaining high TPR and FDR control.
The paper develops methods for high-dimensional inference in Markov random fields.
problem Statistical inference for high-dimensional Markov random fields.
method Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization.
result The proposed methods achieve ℓ1-consistency and false discovery rate control. Complexity measures for neural nets with general activations using path-based norms.
problem Control complexity of neural networks with arbitrary activation functions.
method Approximate general activations with ReLU networks and derive path-based norms for complexity control.
result Preliminary analyses of function spaces and regularized estimators.
In this paper, we propose a novel unsupervised learning method to learn the brain dynamics using a deep learning architecture named residual D-net. As it is often the case in medical research, in contrast to typical deep learning tasks, the size of the resting-state functional Magnetic Resonance Image (rs-fMRI) dataset…
BCD-Net improves PET image reconstruction in low-count scenarios.
problem Low-count PET imaging challenges due to high random fractions and low SNR.
method Modified BCD-Net architecture for iterative neural network-based PET image reconstruction.
result BCD-Net significantly improves CNR and RMSE of reconstructed images compared to traditional methods.
Deep learning system diagnoses AVNFH from plain radiographs.
problem Challenging AVNFH diagnosis from plain radiographs.
method Deep convolutional neural networks for end-to-end diagnosis.
result AVN-net achieves state-of-the-art AUC of 0.97 in AVNFH detection.
In our model, private actors with interbank cash flows similar to, but nore general than (Carmona, Fouque, Sun, 2013) borrow from the outside economy at a certain interest rate, controlled by the central bank, and invest in risky assets. Each private actor aims to maximize its expected terminal logarithmic utility. The…
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
Deep neural nets solve complex insurance math equations.
problem Optimal control problems in insurance math.
method Deep neural network algorithm for elliptic PDEs.
result Solves high-dimensional semilinear elliptic PDEs.
Sustaining efficiency and stability by properly controlling the equity to asset ratio is one of the most important and difficult challenges in bank management. Due to unexpected and abrupt decline of asset values, a bank must closely monitor its net worth as well as market conditions, and one of its important concerns …
Unified approach to sampling and inference for generative models with latent diffusions.
problem Efficient sampling and inference in generative models with latent diffusions.
method Unified stochastic control viewpoint, multilayer feedforward neural nets for drift, unbiased simulation scheme.
result Efficient sampling from a wide class of terminal target distributions with minimal KL divergence.
Paper uses deep reinforcement learning for adaptive emergency control of power systems.
problem Traditional emergency control schemes are inadequate for modern power grids due to increasing uncertainties.
method Developed deep reinforcement learning (DRL) for adaptive emergency control of power systems.
result Demonstrated excellent performance and robustness of DRL-based emergency control schemes in various scenarios.
Deep neural net solves multi-agent optimal trading problem.
problem Optimal trade execution for multiple agents and assets.
method Residual U-net with self-attention for viscosity solution approximation.
result Neural network approach outperforms finite difference methods.
Study tackles balancing policy switching costs in offline RL.
problem Balancing the cost of policy switching in offline RL.
method Optimal transport ideas and Net Actor-Critic algorithm.
result Demonstrated efficiency on multiple RL benchmarks.
Neural nets improve plasma equilibrium modeling for NSTX-U.
problem Modeling plasma equilibrium and shape control for NSTX-U.
method Developed two neural networks: Eqnet and Pertnet.
result NNs offer faster and more flexible prediction of plasma scenarios.
Paper analyzes how present-bias affects carbon emissions and proposes a method to mitigate it.
problem Present-bias impacts carbon emission patterns towards a net zero target.
method Stochastic control techniques adapted from insurance risk theory.
result Higher present-bias leads to excess emissions, and carbon taxes can reduce emissions but beyond a certain point have diminishing returns.
The paper explores discrete isothermic nets using checkerboard patterns in quadrilateral nets.
problem Defining and understanding discrete isothermic nets in quadrilateral nets.
method Using checkerboard patterns and discrete differential geometry to define and analyze isothermic nets.
result The class of isothermic nets is invariant under dualization and Moebius transformations.
We investigate the common underlying discrete structures for various smooth and discrete nets. The main idea is to impose the characteristic properties of the nets not only on elementary quadrilaterals but also on larger parameter rectangles. For discrete planar quadrilateral nets, circular nets, Q∗-nets and conical…
ML system reduces overdraft fees for Mint users.
problem Overdraft fees burden Americans, leading to financial hardship.
method ML-driven overdraft early warning system (ODEWS).
result Saved $3 million in overdraft fees for Mint customers.
Paper analyzes history-based RL methods for MDPs, introduces a theoretical framework and practical algorithm.
problem Improving RL performance in MDPs using history-based features.
method Theoretical framework for history-based RL, practical algorithm design.
result Practical RL algorithm shows effectiveness on continuous control tasks.
Deep nets outperform shallow nets in complex feature realization.
problem Realizing complex data features with deep nets.
method Refined covering number estimates and analysis of approximation rates.
result Deep nets can improve performance without additional capacity costs for complex features.
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
This paper explores the limits of deep learning in poly-time.
problem Characterizing function distributions that deep learning can or cannot learn efficiently.
method Analysis of SGD and GD-based deep learning approaches, proving universality and non-universality results.
result SGD-based deep learning is efficiently universal, while GD-based is not, especially with large batches.
Discretizes special surfaces using Koenigs nets.
problem Integrable structure of special surfaces.
method Discretisation via Koenigs nets.
result Preserves integrable structure in discretization.
We discuss discretization of Koenigs nets (conjugate nets with equal Laplace invariants) and of isothermic surfaces. Our discretization is based on the notion of dual quadrilaterals: two planar quadrilaterals are called dual, if their corresponding sides are parallel, and their non-corresponding diagonals are parallel.…
Classifies nets with area-preserving transformations into two types.
problem Classifying nets with area-preserving transformations.
method Classification using Combescure transformations and isotropic metric duality.
result Found two classes of nets: cone nets and Koenigs nets.
The paper analyzes strategic irreversible investments with novel dynamic strategies.
problem Tradeoff between preemption incentives and option value of waiting in oligopolistic markets.
method Developed novel Markov perfect equilibrium to handle singular control of optimal investment.
result Simpler strategies lead to a 'preemption trap' with zero net present values.
Deep neural nets solve complex stochastic control problems.
problem Solving stochastic optimal control problems with control multiplicative noise.
method Deep recurrent neural networks and LSTM.
result Deep learning algorithm solves complex stochastic control problems efficiently.