arXiv research

New RL approach learns dynamic VCG mechanisms in unknown MDP environments.

Algorithm learns optimal dynamic mechanisms from data.

Optimizes e-commerce traffic sales by incorporating hidden costs into auction mechanisms.

Noether's framework reveals symmetry-breaking in neural networks.

Innovative ball bearing converts rotary to reciprocating motion.

New mechanism designs regulate herding in financial markets.

Proposes a deep generative model for robust forecasting on sparse multivariate time series.

In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art …

A novel incentive mechanism improves fairness and participation in federated learning.

Study develops a smart contract framework for efficient and fair resource allocation.

Graph neural networks are explained through heat diffusion analogy.

New algorithm learns LQR with $O(\sqrt{T})$ regret using Langevin dynamics and excitation.

Paper connects dynamics of mechanical systems to Reeb dynamics.

DaringFed incentivizes clients in OFL with dynamic rewards under TII.

Unified approach to denoising Markov models for efficient sampling.

Mechanism design for large item sets using topic models.

We present a machine learning framework for modeling protein dynamics. Our approach uses L1-regularized, reversible hidden Markov models to understand large protein datasets generated via molecular dynamics simulations. Our model is motivated by three design principles: (1) the requirement of massive scalability; (2) t…

Enhances neural network dynamics to boost computational capacity.

New method learns population dynamics from snapshots, outperforming existing models.

Paper tackles dynamic behavior of variable topology mechanisms, presenting new transition conditions.

A new mechanism optimizes data marketplace pricing efficiently.

Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…

SYNC learns time-aware causal representations to improve model generalization in evolving domains.

Optimizes bidding strategies for LinkedIn ads across multiple platforms.

Geometric framework explains and controls implicit bias in machine learning.

The paper explores how structured representations influence learning dynamics in neural networks.

A new Dirac algebroid approach for nonholonomic systems.

Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research is focussed on handcrafting complex and larger networks, and the design decisions are often ad-hoc and based on intuition. Some recent research has aimed to demys…

This paper proposes an improved design of the perceptron unit to mitigate the vanishing gradient problem. This nuisance appears when training deep multilayer perceptron networks with bounded activation functions. The new neuron design, named auto-rotating perceptron (ARP), has a mechanism to ensure that the node always…

The paper develops an economic foundation for multi-agent learning in markets.

Deep learning models forecast multiple yield curves with improved accuracy.

Studies geometric mechanics for autonomous and nonautonomous systems.

Paper analyzes dynamics of nonholonomic systems with collisions using variational techniques.

While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of clas…

We design two mechanisms for the recommender system to collect user ratings. One is modified Laplace mechanism, and the other is randomized response mechanism. We prove that they are both differentially private and preserve the data utility.

The paper provides a geometric framework for understanding non-equilibrium thermodynamics.

Paper proposes a framework for token economy simulation and wealth distribution.

Myopic procedures are shown to be asymptotically optimal in ranking and selection problems.

Electrostatics method samples complex distributions deterministically.

Enhances LightGCN for credit bond recommendations with dynamic node embeddings.

The paper uses machine learning to compute rare event probabilities in stochastic systems.

Novel RL approach for molecular design using quantum mechanics.

Physical modeling of robotic system behavior is the foundation for controlling many robotic mechanisms to a satisfactory degree. Mechanisms are also typically designed in a way that good model accuracy can be achieved with relatively simple models and model identification strategies. If the modeling accuracy using phys…

The numerical integration plays a fundamental role in understanding the behaviour of many mechanical systems. In this paper some important aspects of the mechanical integrators on the dynamics of a mechanical system are studied. More specific, we have shown that if that the Lie-Trotter integrator is obtained, in case o…

TRS-ODENs learn dynamics with time-reversal symmetry for more efficient learning.

A novel model-selection method for dynamic networks using synthetic data.

Study shows how diverse investors' learning and preferences shape financial markets.

The paper tackles robust design selection for online experiments under uncertain interference mechanisms.