arXiv research

Paper proposes efficient weight updates for edge nodes with minimal communication.

FedSGM tackles constrained federated learning with unified framework.

New framework provides privacy guarantees for practical federated learning.

PRISM-FCP improves federated prediction robustness against Byzantine attacks.

FedAMD framework improves federated learning with partial client participation.

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

Paper proves CLTs for Q-learning with asynchronous updates.

Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.

New method uses randomized sparse neural networks to solve time-dependent PDEs more accurately and efficiently.

DPFRL uses particle filters for decision making with complex visual observations.

Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …

New method targets vaccines for new variants using Thompson sampling.

Paper introduces robust learning methods using coordinate gradient descent.

Adaptive sparse GP model for non-stationary data.

Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive, we mean that our selection rules are based on the dual residual or the primal-du…

Updating predictive models introduces bias, leading to miscalibration.

A new numerical scheme approximates nonlinear filtering densities for noisy and partial measurements.

This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have \emph{partial} and \emph{noisy} access to the hidden state sequence as side information. This access can be seen as "partial labeling" of …

New method combines Monte Carlo and tensor networks for solving complex equations.

This is a semi--expository update and rewrite of my 1974 AMS AMS Memoir describing Plancherel formulae and partial Dolbeault cohomology realizations for standard tempered representations for general real reductive Lie groups. Even after so many years, much of that Memoir is up to date, but of course there have been a n…

New BED method handles online inference for partially observed dynamical systems.

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, an…

Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.

GFM models neural network training as a dynamical system to forecast final weights.

Flexible framework for optimal trading across multiple asset venues.

Develops a regression model for partially observed dynamic tensor data.

Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…

Model forgets examples; this research predicts which ones to replay.

LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial…

Paper develops efficient Bayesian inference for enzymatic SRNs with LNA metamodel.

NBF combines deep learning with classical filtering for better belief tracking.

Gradient-based methods introduce noise that penalizes models sensitive to weight perturbations.

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…

Recently, there has been a trend to combine independent component analysis and canonical polyadic decomposition (ICA-CPD) for an enhanced robustness for the computation of CPD, and ICA-CPD could be further converted into CPD of a 5th-order partially symmetric tensor, by calculating the eigenmatrices of the 4th-order cu…

We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…

New analysis shows how cross-entropy training shapes attention in transformers.

HS-FNO models non-Markovian PDEs by learning history and future states.

Paper proposes a new PLL framework with a progressive identification algorithm.

Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, a…

Optimizes partial AUC across various FPRs for machine learning models.

The paper addresses nonconvex penalized LAD estimation in partial linear models using DNNs.

A new framework for PPLS combines noise estimation, optimization, and calibration.

This work improves policy-based training by proposing an evaluation balance objective for GFlowNets.

Meta-learning neural networks to solve diverse PDEs efficiently.

We present an information-theoretic framework for solving global black-box optimization problems that also have black-box constraints. Of particular interest to us is to efficiently solve problems with decoupled constraints, in which subsets of the objective and constraint functions may be evaluated independently. For …

Revel tackles safe exploration in RL with verified symbolic policies.

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradi…