arXiv research

Dynamic treatment effects estimated over time using covariate balancing.

Unified formula for training dynamics of linear networks combining lazy and balanced regimes.

Two heuristics solve dynamic multiple travelling salesmen problems.

ADAPT method controls balance between sparse generator and discriminator in GANs.

Employing data on the assessed value of land in 1983 -- 2005 Japan, we investigate the dynamical behavior in the high scale region of non-equilibrium systems. From the detailed quasi-balance and Gibrat's law, we derive a relation between the change of Pareto index and a symmetry in the detailed quasi-balance. The relat…

In \cite{D3}, Donaldson defines a dynamical system on the space of Fubini-Study metrics on a polarized compact Kähler manifold. Sano proved that if there exists a balanced metric for the polarization, then this dynamical system always converges to the balanced metric (\cite{S}). In \cite{DKLR}, Douglas, et. al., conjec…

Paper explores balancing market dynamics and interpretable forecasting models for energy prices.

This work is devoted to modelling and identification of the dynamics of the inter-sectoral balance of a macroeconomic system. An approach to the problem of specification and identification of a weakly formalized dynamical system is developed. A matching procedure for parameters of a linear stationary Cauchy problem wit…

We develop an efficient sampling method by simulating Langevin dynamics with an artificial force rather than a natural force by using the gradient of the potential energy. The standard technique for sampling following the predetermined distribution such as the Gibbs-Boltzmann one is performed under the detailed balance…

MTAdam optimizes multiple loss terms in neural models, balancing gradients dynamically.

TV-SurvCaus improves causal inference for dynamic treatments in survival analysis.

New method predicts graph structure changes over time.

The paper proposes Tier Balancing for dynamic fairness in decision-making.

In this work we show that the systems of balance equations (balance systems) of continuum thermodynamics occupy a natural place in the variational bicomplex formalism. We apply the vertical homotopy decomposition to get a local splitting (in a convenient domain) of a general balance system as the sum of a Lagrangian pa…

New deep learning method improves financial stress testing accuracy.

Researchers derive a new equation for valuing American options.

CBDA improves active learning for semantic segmentation, especially with imbalanced classes.

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial intelligent systems. However, neural networks suffer from catastrophic forgetting when…

In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The sto…

Analyzes Indian commercial dynamism using time series data.

AlphaZero assesses new chess variants for balance and dynamics.

We investigate the dynamical behavior in the large scale region of non-equilibrium systems, by employing data on the assessed value of land in 1983 -- 2006 Japan. In the system we find the detailed quasi-balance, which has the symmetry: x_1 -> a {x_2}^θ (x_1 and x_2 are two successive land prices). By using the detaile…

Regularization leads to balancedness in deep linear networks.

Model for open, decentralized network with task load balancing.

WiGS improves active learning for regression by dynamically selecting informative samples.

New method dynamically adjusts UTD ratio to balance under- and overfitting in RL.

New model reveals balance crucial for robust neural coding.

New insights into how large learning rates affect transformer training dynamics.

Diffusion models learn balanced data representations, unlike classification models.

SGD in DLNs reveals feature learning dynamics.

New algorithm balances personalization and statistical validity in MRTs.

Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.

Study compares empirical systemic risk with balance sheet risk in interbank networks.

A new XVA strategy rooted in balance sheet perspective improves equity process for bank shareholders.

Paper introduces multitask neural networks for efficient stochastic control problems.

Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.

Paper uses DRL to optimize portfolios, balancing risk and return.

A RL framework selects features to balance bias and accuracy dynamically.

We consider the relationship between economic activity and intervention, including monetary and fiscal policy, using a universal dynamic framework. Central bank policies are designed for growth without excess inflation. However, unemployment, investment, consumption, and inflation are interlinked. Understanding dynamic…

Surprise describes a range of phenomena from unexpected events to behavioral responses. We propose a measure of surprise and use it for surprise-driven learning. Our surprise measure takes into account data likelihood as well as the degree of commitment to a belief via the entropy of the belief distribution. We find th…

The paper explores how symmetries and noise in SGD influence parameter dynamics.

Proposes a method to balance fairness and utility in ranking models.

We study Smoothed Online Convex Optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a $Ω(\sqrt{d})$ lower bound on the competitive ratio of any online algorithm, where $d$ is the dimension of the action space, we ask under what conditio…

Improves video search by balancing text and visual modalities.

In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the…

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman al…

New Ricci flow method for directed graphs with balancing factor.

In this work, we present a numerical method based on a sparse grid approximation to compute the loss distribution of the balance sheet of a financial or an insurance company. We first describe, in a stylised way, the assets and liabilities dynamics that are used for the numerical estimation of the balance sheet distrib…