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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “update rule”
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.
A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations us…
New learning rule simplifies Bayesian updates for deep learning.
problem Bayesian learning rule's complexity and manifold constraints.
method Lie-group approach to simplify Bayesian updates.
result New algorithm learns sparse features in deep learning.
MTL2L learns to adapt optimisation rules for unseen data.
problem Learners need to adapt to unseen data domains.
method Introduces MTL2L, a context-aware neural optimiser.
result MTL2L can adapt optimisation rules for unseen data.
When Is Generalized Bayes Bayesian? A Decision-Theoretic Characterization of Loss-Based Updatingstat.ME
New decision-theoretic characterization separates belief and decision posteriors.
problem Understanding the conditions under which loss-based updating coincides with Bayesian updating.
method Decision-theoretic approach to distinguish belief and decision posteriors.
result Generalized Bayes coincides with ordinary Bayesian updating only if the loss is proportional to negative log-likelihood.
The study learns neural update rules by remembering past experiences.
problem Developing efficient online learning rules for neural networks.
method Representing neurons with vectors, using meta-neural networks for updates, and training for remembering past experiences.
result The approach reveals insights into learning rules and could be used for complex tasks like episodic memory.
Adversarial training is a technique for training robust machine learning models. To encourage robustness, it iteratively computes adversarial examples for the model, and then re-trains on these examples via some update rule. This work analyzes the performance of adversarial training on linearly separable data, and prov…
Study on incentivizing truthfulness in federated learning with heterogeneous data.
problem Manipulated updates in federated learning due to data heterogeneity.
method Formulated a game-theoretic approach to prevent clients from misreporting their gradient updates.
result Developed a payment rule that provably disincentivizes sending modified updates in federated learning.
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…
An online decision-making algorithm using stochastic gradient descent for big data.
problem Efficiently updating decision rules in online decision making with big data.
method Stochastic gradient descent for online updates, asymptotic normality of estimators.
result Asymptotic normality of parameter and value estimators, enabling statistical inference.
Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive …
Nonnegative matrix factorization (NMF), a dimensionality reduction and factor analysis method, is a special case in which factor matrices have low-rank nonnegative constraints. Considering the stochastic learning in NMF, we specifically address the multiplicative update (MU) rule, which is the most popular, but which h…
Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a neural network that directly produces updates or by attempting to learn better i…
Recent years have witnessed the rapid development of block coordinate update (BCU) methods, which are particularly suitable for problems involving large-sized data and/or variables. In optimization, BCU first appears as the coordinate descent method that works well for smooth problems or those with separable nonsmooth …
The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machine learning frameworks have largely ignored the possibility of arbitrary (i.e., Byzantine) failures. In this paper, we study the robustness …
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
Rule-State Inference (RSI): A Bayesian Framework for Compliance Monitoring in Rule-Governed Domainscs.LG
RSI uses Bayesian inference to monitor compliance in rule-governed domains.
problem Structural obstacles in compliance monitoring, including unlabeled outcomes and selective withholding of evidence.
method Rule-State Inference (RSI) treats formalized rules as Bayesian priors and infers compliance states through mean-field variational inference.
result RSI delivers formal guarantees of adaptability, consistency, and convergence, validated on a synthetic enterprise benchmark.
Non-affine aggregation rules cannot preserve monotonicity in convex learning.
problem Designing non-affine aggregation rules that maintain monotonicity in convex learning.
method Proving that monotonicity of aggregated gradients is preserved only if the aggregation rule is positively affine.
result Non-affine aggregation prevents steady convergence and substantially degrades algorithmic stability.
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.
New priors can update posteriors without re-estimating likelihoods.
problem Degradation of classification approaches when class priors change.
method Recompute posteriors using recovered likelihoods from original posteriors and new priors.
result Dynamic update of original posteriors is possible without re-estimating likelihoods.
Improved greedy 2-coordinate updates for optimization problems with constraints.
problem Minimizing smooth functions subject to constraints.
method Exploiting a connection to steepest descent in the 1-norm, we give faster convergence rates and efficient computation.
result Greedy selection converges faster than random selection and can be computed in time.
Test-time training adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
problem Improving accuracy of pretrained models under distribution shifts.
method Explaining TTT behavior through a decision-theoretic lens.
result TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions.
Paper proposes a math-inspired L2O model for better generalization.
problem Overfitting and poor generalization of generic L2O models.
method Derived mathematical conditions for successful update rules and proposed a novel L2O model.
result Proposed model outperforms generic L2O models in out-of-distribution settings.
In this paper we provide a flexible framework allowing for a unified study of time consistency of risk measures and performance measures (also known as acceptability indices). The proposed framework not only integrates existing forms of time consistency, but also provides a comprehensive toolbox for analysis and synthe…
Bayesian neural networks update beliefs with soft evidence, improving accuracy and calibration.
problem Updating neural network weights with uncertain or soft evidence.
method Developed two algorithms to approximate Jeffrey's rule for updating neural network weights.
result Jeffrey-based methods outperform traditional approaches in accuracy and calibration, especially in noisy data.
Research Issues in Mining User Behavioral Rules for Context-Aware Intelligent Mobile Applicationscs.LG
Context-awareness in smart mobile applications is a growing area of study, because of it's intelligence in the applications. In order to build context-aware intelligent applications, mining contextual behavioral rules of individual smartphone users utilizing their phone log data is the key. However, to mine these rules…
EP learns like BPTT but with local weight updates.
problem Existing EP lacks a local time learning rule.
method C-EP updates weights simultaneously with neuron dynamics.
result C-EP follows BPTT gradients and performs well.
A new principle for optimizer selection improves training speed and performance.
problem Finding the best optimizer hyperparameters for faster training.
method Formulate optimizer selection as maximizing the expected drop rate in loss, treating gradients and updates as signals and an optimizer as a causal filter.
result Greedy optimizer selection yields stable and effective momentum rules.
Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…
A novel Bayesian computation method using importance weighting improves numerical stability and performance.
problem Bayesian computation stability and performance issues.
method Nonparametric approach via feature means, importance weighting, and kernel Bayes' rule.
result Importance weighted kernel Bayes' rule yields superior numerical stability and performance.
GAIT-prop derives a biologically plausible learning rule from backpropagation.
problem Biological implausibility in traditional backpropagation for neural networks.
method GAIT-prop uses a top-down model to convert output error into plausible targets for weight updates.
result GAIT-prop and backpropagation give identical weight updates under certain conditions.
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.
We analyze SA with Markovian data and nonlinear updates, overcoming prior limitations.
problem Analyzing stochastic approximation with Markovian data and nonlinear updates.
method Fine-grained analysis of SA iterates and Markovian data, leveraging smoothness and recurrence properties.
result Established weak convergence and precise asymptotic bias of SA iterates.
The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…
We introduce a new weight-decay scaling rule to maintain sublayer gains across different widths in modern scale-invariant architectures.
problem In modern scale-invariant architectures, training quickly enters a steady state where normalization layers create backward scale sensitivity, degrading learning-rate transfer.
method We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths by equalizing the effective learning rate.
result Our empirical weight-decay scaling rule approximately keeps sublayer gains width invariant, enabling zero-shot transfer of learning rate and weight decay.
This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building blocks are detailed. The forward pass and the update rules for the backpropagation algorithm are then der…
The condensed nearest neighbor (CNN) algorithm is a heuristic for reducing the number of prototypical points stored by a nearest neighbor classifier, while keeping the classification rule given by the reduced prototypical set consistent with the full set. I present an upper bound on the number of prototypical points ac…
A new gradient boosting method improves interpretability of probabilistic models.
problem Learning interpretable yet accurate probabilistic models with limited rule complexity.
method A new objective function that measures the angle between risk gradient and condition output vector projection.
result Significantly improves comprehensibility/accuracy trade-off of fitted ensemble.
Optimal Volt/VAR control rules are designed using deep neural networks.
problem Designing optimal Volt/VAR control rules for distributed energy resources (DERs).
method Formulate optimal rule design as a bilevel program, then reformulate it as training a deep neural network (DNN). Use proximal gradient descent (PGD) iterations to emulate Volt/VAR dynamics.
result The proposed solution can be adapted to single/multi-phase feeders and achieves enhanced steady-state voltage profiles.
Biological neural network mimics CCA for multi-channel data.
problem Implementing CCA in a biologically plausible neural network.
method Derive an online CCA algorithm with local synaptic updates for multi-compartmental neurons.
result The derived neural network architecture and synaptic updates resemble cortical pyramidal neuron behavior.
A hyperbolic space has been shown to be more capable of modeling complex networks than a Euclidean space. This paper proposes an explicit update rule along geodesics in a hyperbolic space. The convergence of our algorithm is theoretically guaranteed, and the convergence rate is better than the conventional Euclidean gr…
We propose an active set selection framework for Gaussian process classification for cases when the dataset is large enough to render its inference prohibitive. Our scheme consists of a two step alternating procedure of active set update rules and hyperparameter optimization based upon marginal likelihood maximization.…
We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient learning and testing but more importantly better interpretability and trainability. We…
New optimizer designs respect symmetry, improving deep learning models.
problem Optimizers lack respect for symmetry in neural networks.
method Introduce symmetry-compatible principle for optimizer design.
result Symmetry-compatible optimizers improve model performance.
In the past decade many researchers have proposed new optimal portfolio selection strategies to show that sophisticated diversification can outperform the naïve 1/N strategy in out-of-sample benchmarks. Providing an updated review of these models since DeMiguel et al. (2009b), I test sixteen strategies across six empir…
A new screening rule speeds up OWL regression solving.
problem High-dimensional sparse learning with OWL regression's computational cost and memory usage.
method Safe screening rule for OWL regression using iterative strategy.
result Significant computational gain without accuracy loss.
In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO) optimization setting, where no explicit gradient information is available. Our lea…