Paper proves Jeffrey's update rule minimizes relative entropy.
problem Improving Bayesian learning algorithms.
method More concise proof of Jeffrey's update rule.
result Jeffrey's update rule reduces relative entropy.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “state updates”
A new LSTM model reduces state updates and improves convergence for long sequences.
problem Vanishing gradient problem in RNNs and slow convergence on long sequences.
method Gaussian-gated LSTM (g-LSTM) with a time gate to control neuron updates.
result The g-LSTM model reduces state updates and computes by at least 10x compared to an equivalent LSTM.
The paper addresses Dyna-style RL's value hallucination issue by proposing a new algorithm.
problem Value hallucination in Dyna-style RL due to bootstrapping simulated states.
method Introduces a new Dyna algorithm using predecessor models with multi-step updates.
result Evidence supports the Hallucinated Value Hypothesis (HVH), suggesting predecessor models with multi-step updates are promising.
We consider 1-qubit mixed quantum state estimation by adaptively updating measurements according to previously obtained outcomes and measurement settings. Updates are determined by the average-variance-optimality (A-optimality) criterion, known in the classical theory of experimental design and applied here to quantum …
Paper improves policy updates in reinforcement learning to speed up learning.
problem Slow learning and unlearning in policy optimization.
method Introduces a novel gradient update and a modified policy update.
result Proves modified policy update converges to global optimality.
Selective state-adaptive regularization improves offline RL performance.
problem Extrapolation errors and value overestimation in static dataset RL.
method State-adaptive regularization coefficients trust Bellman-driven results selectively.
result Significant improvement in performance on D4RL benchmark.
A new policy improvement method using CEM for Actor-Critic.
problem Improving policy efficiency and robustness in reinforcement learning.
method Greedy Actor-Critic (Greedy AC) using Conditional Cross-Entropy Method (CCEM).
result Greedy AC outperforms Soft Actor-Critic and is less sensitive to entropy regularization.
In this letter, we generalize the convolutional NMF by taking the -divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the -NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…
Paper develops efficient methods for covariance updates and belief space planning.
problem Efficiently updating covariance and evaluating belief space planning in high-dimensional state spaces.
method Novel incremental covariance update technique and factor-graph action tree approach.
result State-of-the-art methods for covariance updates and belief space planning are improved.
Flora uses random projections to achieve high-rank updates with low memory usage.
problem Excessive memory usage in large neural networks during training.
method Flora approximates LoRA using random projections to enable high-rank updates with sublinear space complexity.
result Flora achieves high-rank updates with significantly reduced memory usage compared to LoRA.
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…
State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent Neural Network (RNN), which updates the internal state using the current internal state and the most recent observation. This internal state…
Tensor networks and RNNs are equivalent, improving wave function encoding.
problem Efficiently encoding quantum states in neural networks.
method Generalized RNN architecture for tensor networks, supporting polynomial time wave function evaluation.
result Tensorial RNNs can encode quantum states with lower bond dimensions and higher accuracy.
Many nonlinear extensions of the Kalman filter, e.g., the extended and the unscented Kalman filter, reduce the state densities to Gaussian densities. This approximation gives sufficient results in many cases. However, this filters only estimate states that are correlated with the observation. Therefore, sequential esti…
This paper considers the actor-critic contextual bandit for the mobile health (mHealth) intervention. The state-of-the-art decision-making methods in mHealth generally assume that the noise in the dynamic system follows the Gaussian distribution. Those methods use the least-square-based algorithm to estimate the expect…
GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions include those used in both Goodfellow's original GAN and the WGAN-GP. To formally d…
State evolution beyond first-order methods I: Rigorous predictions and finite-sample guaranteesmath.ST
New method predicts state evolution for non-first-order algorithms on nonconvex problems.
problem Analyzing nonconvex optimization problems with random data.
method Developed a state evolution for a broader class of algorithms including first-order and saddle point updates.
result Established rigorous state evolution predictions and finite-sample guarantees for non-first-order methods.
The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.
problem Approximating complex multi-agent reinforcement learning dynamics in finite-state Markov games.
method Rescaling learning process by reducing learning rate and increasing update frequency, proving convergence to an ODE.
result The rescaled process converges to an ODE that approximates the agent's learning dynamics.
Percolation on complex networks has been used to study computer viruses, epidemics, and other casual processes. Here, we present conditions for the existence of a network specific, observation dependent, phase transition in the updated posterior of node states resulting from actively monitoring the network. Since tradi…
Online DEM improves tracking of latent states in dynamic systems.
problem Tracking latent states in dynamic systems with online updates.
method Specializes DEM for online data assimilation, separating temporal scales.
result ODEM can track latent states of a non-linear generative model.
Tensor decompositions are invaluable tools in analyzing multimodal datasets. In many real-world scenarios, such datasets are far from being static, to the contrary they tend to grow over time. For instance, in an online social network setting, as we observe new interactions over time, our dataset gets updated in its "t…
Improved HGF networks avoid negative precision errors in volatility updates.
problem Negative posterior precision errors in volatility-coupled nodes of HGF networks.
method Introduced a modified quadratic approximation to variational energy.
result Robust update equations across parameter space that track posterior faithfully.
A modern Hopfield network improves deep learning with better memory and attention.
problem Improving memory and attention mechanisms in deep learning.
method Introducing a new Hopfield network with continuous states and a novel update rule.
result The new Hopfield network can store and retrieve patterns efficiently with low errors.
Develops a new method for optimizing policies in hierarchical models.
problem Optimizing complex policies in hierarchical models.
method Applies second-order methods in the space of state-action paths.
result The natural path gradient method can be computed exactly and reflects state-space hierarchy.
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…
A new technique updates weights multiple times for online learning, reducing mistakes to near zero.
problem Online learning with partial data and unknown future data points.
method Iterative weight updating for the same instance.
result Reduced mistake rate to near zero for various datasets and algorithms.
Paper proves CLTs for Q-learning with asynchronous updates.
problem Establishing convergence rates for Q-learning algorithms.
method Polyak-Ruppert averaging, non-asymptotic and functional CLTs.
result Convergence rates in Wasserstein distance for Q-learning.
Marginalized particle Gibbs for multiple state-space models coupled through shared parametersstat.ME
New PG samplers improve inference in coupled state-space models.
problem Bayesian inference from multiple time series with shared parameters.
method Marginalized Particle Gibbs samplers for coupled state-space models.
result Improved parameter inference through shared information.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
All-goals updating exploits the off-policy nature of Q-learning to update all possible goals an agent could have from each transition in the world, and was introduced into Reinforcement Learning (RL) by Kaelbling (1993). In prior work this was mostly explored in small-state RL problems that allowed tabular representati…
A new method reduces communication costs in decentralized optimization.
problem Decentralized optimization with non-convex cost functions.
method LU-GT method with local updates.
result LU-GT achieves the same communication complexity as Federated Learning and maintains solution quality.
Robust state-space radio interferometric imaging using Stochastic Approximation Expectation Maximization
problem Improving state-space radio interferometric imaging in the presence of heavy-tailed noise
method Stochastic Approximation Expectation Maximization
result Significant improvement in reconstruction fidelity and robustness to radio-frequency interference
Drop-Muon updates only some layers, speeding up training.
problem Conventional deep learning optimizers update all layers at once, which can be inefficient.
method Drop-Muon updates only a subset of layers per step, with randomized schedules.
result Drop-Muon achieves up to 1.4x faster training time with similar accuracy.
A new model detects anomalies in time series data efficiently.
problem Detect anomalies in high-dimensional time series data.
method r-ssGPFA, an unsupervised online anomaly detection model using state space Gaussian processes.
result The model detects anomalies efficiently and is computationally cheaper.
Study how learning impacts decision-making in project expansion.
problem Optimal timing of expansion decisions based on uncertain project profitability.
method Bayesian updating model with two irreversible alternatives (exit or expansion).
result Time-to-decision is not monotonic with information arrival rate.
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.
Mathematical methods characterize RNNs' asymptotics as hidden units and data grow.
problem Characterize recurrent neural networks' behavior as hidden units and data grow.
method Developed mathematical methods to analyze RNNs' convergence to an infinite-dimensional ODE coupled with a fixed point of a random algebraic equation.
result RNNs converge to an infinite-dimensional ODE coupled with a fixed point of a random algebraic equation.
Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updat…
We show that a simple model of a spatially resolved evolving economic system, which has a steady state under simultaneous updating, shows stable oscillations in price when updated asynchronously. The oscillations arise from a gradual decline of the mean price due to competition among sellers competing for the same reso…
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole episode and successively propagates the value of a state to its previous states.…
New method for density estimation without approximating posterior distributions.
problem Challenges in non-smooth data distributions for Bayesian density estimation.
method Autoregressive likelihood decomposition and Gaussian process prior in a quasi-Bayesian framework.
result Achieves state-of-the-art results in small-data regimes.
Ensuring Monotonic Policy Improvement in Entropy-regularized Value-based Reinforcement Learningcs.LG
This paper improves reinforcement learning policies in a scalable way.
problem Ensuring monotonic policy improvement in entropy-regularized RL.
method Derives an entropy-aware lower bound and proposes a novel RL algorithm.
result Demonstrates effectiveness in continuous-state tasks using a linear function approximator.
Proposes variational Gaussian approximations for solving the Kushner equation.
problem Solving the Kushner equation for state estimation with observations.
method Tractable variational Gaussian approximations of proximal losses based on Wasserstein and Fisher metrics.
result The proposed method leads to a Gaussian flow consistent with Kalman-Bucy and Riccati flows.
SQuARM-SGD improves decentralized SGD efficiency with momentum.
problem Efficient decentralized training of large-scale models over networks.
method Fixed local SGD steps with Nesterov's momentum, sparsified and quantized updates, locally computed triggering criterion.
result Convergence rate matches vanilla SGD, momentum improves test performance.
ROIPCA and fROIPCA are online PCA algorithms using rank-one updates.
problem Memory-restricted online PCA for large or streaming data.
method ROIPCA and fROIPCA use rank-one updates for efficient computation.
result fROIPCA is faster with comparable accuracy; ROIPCA is more accurate.
PLUMAGE improves large model training efficiency and stability.
problem Accelerator memory and networking constraints during large model training.
method Probabilistic Low rank Unbiased Minimum Variance Gradient Estimator (PLUMAGE) that resolves bias and variance issues.
result PLUMAGE reduces training loss by 28% on average across the GLUE benchmark.
Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.
Introduces expected eligibility traces for more efficient credit assignment in reinforcement learning.
problem Efficiently assigning credit to states and actions in reinforcement learning.
method Introduces expected eligibility traces, allowing updates to counterfactual sequences.
result Substantial improvements in temporal-difference learning can be achieved with expected traces.