arXiv research

A new correction term improves sample efficiency in deep reinforcement learning.

New SGD algorithm finds critical points faster with second-order corrections.

UCBMQ improves Q-learning by adding momentum to correct bias and limit regret.

Proposes EDM algorithm to accelerate model training in distributed networks.

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant directions in parameter updating, which can minify the oscillations of parameter…

We show that it is possible to perturb arbitrary vacuum asymptotically flat spacetimes to new ones having exactly the same energy and linear momentum, but with center of mass and angular momentum equal to any preassigned values measured with respect to a fixed affine frame at infinity. This is in contrast to the axisym…

Study forecasts vegetable prices in Nepal using a novel index and ensemble model.

In this paper the relation between the choice of a differential structure and a smooth connection in the tangential bundle is discussed. For the case of an exotic $S^7$ one obtains corrections to the curvature after the change of the differential structure, which can not be neglected by a gauge transformation. In the m…

Researchers resolved ambiguities in gravitational radiation charges.

Tractor Calculus is a powerful tool for analyzing Weyl invariance; although fundamentally linked to the Cartan connection, it may also be arrived at geometrically by viewing a conformal manifold as the space of null rays in a Lorentzian ambient space. For dimension d conformally flat manifolds we show that the (d+2)-di…

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …

Paper corrects and expands stochastic Lie systems theory.

The study finds that factor momentum is significant only at short lags compared to stock momentum.

We test the price momentum effect in the Korean stock markets under the momentum universe shrinkage to subuniverses of the KOSPI 200. Performance of the momentum strategy is not homogeneous with respect to change of the momentum universe. It is found that some submarkets generate the higher momentum returns than other …

Geometric formalism views optimization algorithms as discrete connections, revealing their algebraic curvature and flatness properties.

Gradient Boosting Machine (GBM) is an extremely powerful supervised learning algorithm that is widely used in practice. GBM routinely features as a leading algorithm in machine learning competitions such as Kaggle and the KDDCup. In this work, we propose Accelerated Gradient Boosting Machine (AGBM) by incorporating Nes…

Introduces homotopy momentum sections on multisymplectic manifolds.

Study tests five popular trading signal families and finds four refuted, one inconclusive, and one not refuted.

Customer momentum is a positive relationship between a firm's returns and past returns of its customers.

This paper examines momentum spillover across multiple asset classes using only pricing data.

The paper analyzes how hyperparameters affect SGD with momentum's convergence rate.

This paper presents generalized momentum mappings for covariant Hamiltonian field theories. The new momentum mappings arise from a generalization of symplectic geometry to $L_VY$, the bundle of vertically adapted linear frames over the bundle of field configurations $Y$. Specifically, the generalized field momentum obs…

We give a detailed discussion about existence and uniqueness of Lu's momentum map. More precisely, we introduce the infinitesimal momentum map, and we study its properties. This allows us to describe the theory of reconstruction of the momentum map from the infinitesimal one. We provide the conditions for the uniquenes…

Momentum ResNets improve ResNets' memory efficiency.

Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suff…

We introduce various quantitative and mathematical definitions for price momentum of financial instruments. The price momentum is quantified with velocity and mass concepts originated from the momentum in physics. By using the physical momentum of price as a selection criterion, the weekly contrarian strategies are imp…

New algorithm Momentum-QNG improves optimization of quantum circuits.

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to…

Momentum speeds up evolutionary processes in machine learning.

Contact manifolds' momentum polytopes are convex.

Unified model learns from both time-series and cross-sectional momentum features.

SMG combines shuffling and momentum for non-convex optimization.

New method shows stochastic momentum can converge quickly on optimization problems.

The paper analyzes dynamics of momentum in high dimensions with sparse updates.

One has not any conventional energy-momentum conservation law in Lagrangian field theory, but relations involving different stress-energy-momentum tensors associated with different connections. It is not obvious how to choose the true energy-momentum tensor. This problem is solved in the framework of the multimomentum …

The paper extends a theorem about momentum maps to singular symplectic spaces.

The use of momentum in stochastic gradient methods has become a widespread practice in machine learning. Different variants of momentum, including heavy-ball momentum, Nesterov's accelerated gradient (NAG), and quasi-hyperbolic momentum (QHM), have demonstrated success on various tasks. Despite these empirical successe…

This paper analyzes momentum Q-learning with finite-sample guarantees.

It is well-known that irreversible MCMC algorithms converge faster to their stationary distributions than reversible ones. Using the special geometric structure of Lie groups $\mathcal G$ and dissipation fields compatible with the symplectic structure, we construct an irreversible HMC-like MCMC algorithm on $\mathcal G…

Generalizes momentum map to Courant algebroid for constrained mechanics.

Momentum improves deep learning generalization by stabilizing noise and learning features.

Momentum SGD fails to track nonstationary optima due to drift amplification.

This paper concentrates on the time series momentum or contrarian effects in the Chinese stock market. We evaluate the performance of the time series momentum strategy applied to major stock indices in mainland China and explore the relation between the performance of time series momentum strategies and some firm-speci…

A new accelerated method with simpler momentum update rules.

New method uses momentum to converge in DC optimization with small batches.

Dynamic econometric models improve trading signals in momentum strategies.

A technique identifies memoryless algorithms approximating memory-dependent optimization methods.

Stochastic proximal point algorithm with momentum converges faster and is more stable than standard methods.