Convolutional networks improve reinforcement learning for navigating all goals.
problem Expensive parallel updates limit reinforcement learning to small tabular cases.
method Use convolutional neural networks to generate Q-values and updates for all goals simultaneously.
result Demonstrated improved accuracy and generalization on various environments.
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…
Reward suffices for convex MDPs, expanding RL to new problems.
problem Capturing goals as convex functions of stationary distribution.
method Reformulated as a min-max game using Fenchel duality.
result Convex MDPs require non-stationary reward functions.
Framework evaluates quality of synthetic data generated with differential privacy.
problem Ensuring synthetic data retains statistical quality after applying differential privacy.
method Developed a framework to evaluate synthetic data quality from a practical researcher's viewpoint.
result Synthetic data can be evaluated against training data or underlying populations, and for specific tasks like inference or prediction.
Paper proposes efficient weight updates for edge nodes with minimal communication.
problem Inefficient and resource-intensive full weight updates for edge nodes.
method Deep partial updating, selecting a subset of weights to update.
result Achieves similar performance with fewer weight updates.
A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.
problem Learning variance and incorrect reference signals in deep reinforcement learning.
method t-soft update method inspired by student-t distribution, which reduces extreme updates and accelerates similar updates.
result The t-soft update method outperforms conventional methods in terms of return and variance in PyBullet robotics simulations.
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.
New implicit Krasulina's k-PCA update avoids QR-decomposition and improves convergence.
problem Online k-PCA problem with orthonormality constraint.
method Derived an implicit form of Krasulina's update that bypasses orthonormality constraint.
result The new update avoids costly QR-decomposition and yields superior convergence.
AMUSE uses reinforcement learning to predict optimal model updates.
problem Concept drift weakens model performance over time.
method Reinforcement learning in a simulated environment.
result AMUSE proactively recommends updates based on performance improvements.
Efficiently updates posterior tree distributions over meta-trees.
problem Updating posterior distributions over meta-trees efficiently.
method Batch updating method for posterior tree distributions.
result More efficient batch updating method.
Unified approach combining gradient descent and multiplicative updates.
problem Combining gradient descent and multiplicative updates for machine learning.
method Introduces hypentropy and a family of matrix-based updates.
result Derives tight regret bounds for the new family of updates.
LD-SGD improves communication in decentralized SGD.
problem Efficiently combining local updates and decentralized communication.
method Proposes LD-SGD integrating local updates and decentralized SGD, with a convergence analysis.
result LD-SGD converges to a critical point for non-convex objectives with non-identically distributed data.
Paper extends 2D β-CNMF with exact multiplicative updates.
problem Improving nonnegative matrix factor deconvolution for 2D data.
method Derives exact multiplicative updates for β-CNMF factors. result The updates lead to monotonically decreasing β-divergence. The paper examines how updates to probabilistic models influence behavior based on evidence.
problem Understanding how updates to probabilistic models influence behavior based on evidence.
method Study of KL-regularized soft updates as Bayesian posterior updates within a single probabilistic model.
result Posterior updates determine relative incentives but not absolute rewards, which are ambiguous up to context-specific baselines.
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.
Proposes a new method for nonlinear Bayesian updates using ensemble kernel regression.
problem Nonlinear and non-Gaussian Bayesian updates for complex systems.
method Combines Kalman filtering for observed components and kernel density estimation for unobserved components, with subsampling and clustering.
result Reduces estimation errors in highly nonlinear scenarios compared to standard linear updates.
In this paper, we study the randomized distributed coordinate descent algorithm with quantized updates. In the literature, the iteration complexity of the randomized distributed coordinate descent algorithm has been characterized under the assumption that machines can exchange updates with an infinite precision. We con…
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
Paper compresses neural network weight-updates for image artifacts removal.
problem Efficiently compressing neural network weight-updates for image artifacts removal.
method Fine-tuning a pre-trained artifact removal network on target data with a compression objective that encourages sparse and quantized weight-updates.
result Achieves reconstruction quality comparable to traditional codecs at comparable bitrates.
In this letter, we generalize the convolutional NMF by taking the β-divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the β-NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…
End-to-end encrypted neural network improves privacy and compression in federated learning.
problem Privacy and bandwidth issues in gradient updates transmission in federated learning.
method Proposes an end-to-end encrypted neural network to encode and decode gradient updates.
result Effective privacy protection and data compression with minimal accuracy loss.
EnKF's update is shown to be similar to Matheron's method in Gaussian process regression.
problem Data assimilation in high-dimensional systems.
method Empirical Matheron update applied to EnKF.
result Ensemble Kalman Filter's update is equivalent to an empirical Matheron update.
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.
Algorithm estimates bounds of updated classifier coefficients efficiently.
problem Determining sensitivity of updated classifiers without retraining.
method Proposes an algorithm to estimate upper and lower bounds of updated classifier coefficients.
result Estimates bounds with low computational complexity and tightness.
Develops efficient method for updating models with small data changes.
problem Efficiently updating models when data changes (e.g., adding/removing instances/features).
method Generalized Low-Rank Update (GLRU) for non-linear estimators.
result Provides updated solutions with computational complexity proportional to dataset changes.
Paper studies efficient regression for dynamic graphs.
problem Regression over dynamic graphs.
method Update-efficient matrix embedding, O(nm) time complexity for updates.
result Exact optimal solution can be updated efficiently in dynamic graphs.
Analysis of model updates reveals sensitive data leaks.
problem Information leakage during model updates.
method Differential analysis of language model snapshots.
result New metrics (differential score, differential rank) reveal sensitive data leaks.
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…
A new method improves few-shot image classification by updating top layers.
problem Few-shot image classification with limited data.
method Layer-wise adaptive updating (LWAU) for meta-learning.
result LWAU outperforms existing methods with a clear margin and learns more efficiently.
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.
Study examines auditing fairness in evolving models, identifying strategic updates that preserve audit properties.
problem Auditing fairness in machine learning models that adapt to changing environments.
method Characterizes strategic updates that preserve audit properties, proposes a generic PAC auditing framework.
result Establishes distribution-free auditing bounds for statistical parity using the SP dimension.
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.
This work analyzes how often to update the target network in Q-learning.
problem Understanding the optimal frequency of target network updates in Q-learning.
method Formulated target updates as a nested optimization scheme, derived finite-time convergence analysis.
result Optimal target update frequency increases geometrically over time.
Deep networks trained with Hebbian updates perform similarly to back-propagation on image datasets.
problem Training deep networks with realistic asymmetric connections and updates.
method Use Hebbian updates with separate feedforward and feedback weights, and local rule for updates.
result Similar performance to back-propagation achieved with Hebbian updates on challenging image datasets.
AI updates can disrupt human-AI teams; new objective improves compatibility.
problem AI updates can disrupt human-AI team performance.
method Introduce compatibility concept, propose re-training objective.
result Current machine learning algorithms do not produce compatible updates.
Framework for safely updating machine learning models.
problem Continuous updates to machine learning models can lead to unintended consequences.
method Formalizes the problem as computing the largest locally invariant domain (LID), uses tractable primal-dual formulation.
result Matches or exceeds heuristic baselines for avoiding forgetting while providing formal safety guarantees.
Reparameterizes mirror descent as gradient descent for efficient sparse learning.
problem Efficiently training small sparse networks with mirror descent.
method Develops a framework to convert mirror descent updates into gradient descent updates on different parameters.
result Mirror descent can be reparameterized as gradient descent on modified parameters, facilitating standard backpropagation.
A new graph neural network (NBA-GNN) avoids revisiting nodes to improve accuracy.
problem Redundancy in graph neural network updates causes over-squashing and inaccurate recognition.
method Proposes non-backtracking graph neural networks (NBA-GNN) that update messages without revisiting nodes.
result The NBA-GNN alleviates over-squashing and improves performance on graph benchmarks.
FedLoRU improves FL efficiency by using low-rank updates.
problem Communication inefficiency and performance reduction in Federated Learning.
method Proposes FedLoRU, a low-rank update framework for FL, which reduces communication costs while maintaining performance.
result FedLoRU achieves convergence rates similar to FedAvg and is robust to heterogeneous and large numbers of clients.
Paper analyzes ensemble Kalman updates for effective dimension and localization.
problem Why small ensemble sizes work well in inverse problems and data assimilation.
method Non-asymptotic analysis of ensemble Kalman updates, focusing on effective dimension and localization.
result Rigorously explains why a small ensemble size is sufficient when prior covariance has moderate effective dimension.
SUMER updates deployed models with new data, improving performance.
problem Updating deployed machine learning models with new data is difficult.
method SUMER uses semi-supervised learning and noise remediation to iteratively retrain models.
result SUMER improves model performance, especially with limited initial training data.
The thesis clarifies when local updates outperform centralized methods in heterogeneous data environments.
problem Understanding when local updates are more effective than centralized or mini-batch methods in distributed optimization.
method Fine-grained consensus-error-based analysis framework, focusing on bounded second-order heterogeneity and third-order smoothness.
result Local updates outperform centralized or mini-batch methods under realistic models of data heterogeneity.
Develops local population-risk certificates for model updates
problem Model updates in machine learning
method Certify population-risk increments around a model
result Certified upper endpoint yields a risk-controlled update rule
We describe k-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…
Gradient methods converge better for alternating updates in bilinear zero-sum games.
problem Understanding the dynamics of gradient algorithms for bilinear zero-sum games.
method Systematic analysis of popular gradient updates for simultaneous and alternating versions of bilinear zero-sum games.
result Alternating updates converge better than simultaneous ones, with optimal parameter setup and rates.
The paper bounds generalization error for iterative learning with bounded updates.
problem Generalization error of iterative learning algorithms with bounded updates for non-convex loss functions.
method Information-theoretic techniques, reformulating mutual information as update uncertainty, variance decomposition.
result Improved generalization error bounds for iterative learning algorithms with bounded updates.
Two algorithms for linear contextual bandits with rare updates achieve optimal regret and efficiency.
problem Linear contextual bandits with infrequent parameter updates.
method Two practical algorithms with O(loglogT) updates, BLCE-G and BLCE. result Minimax-optimal regret with low computational complexity.
EigenGame improves eigendecomposition by offering unbiased updates for larger datasets.
problem Minibatch bias in EigenGame limits convergence and parallelism.
method Proposed unbiased stochastic update for EigenGame.
result Asymptotic equivalence to EigenGame, greater parallelism, and improved performance.