Survey on importance weighting in machine learning applications.
problem Distribution shift in supervised learning.
method Weighting objective function or probability distribution based on instance importance.
result Importance weighting can guarantee desirable statistical properties in distribution shift scenarios.
A new meta-learning framework that assigns weights to source tasks based on target samples.
problem Learning initialization for target tasks with limited labeled examples.
method A general framework that assigns weights to the loss of different source tasks, which can depend on the target samples. Provides upper bounds and develops a learning algorithm based on minimizing the error bound with respect to an empirical IPM.
result Empirically, the weighted meta-learning algorithm finds better initializations than uniformly-weighted meta-learning algorithms.
Current algorithms for deep learning probably cannot run in the brain because they rely on weight transport, where forward-path neurons transmit their synaptic weights to a feedback path, in a way that is likely impossible biologically. An algorithm called feedback alignment achieves deep learning without weight transp…
Algorithm learns which weights to share in deep multi-task learning.
problem Difficulty in deciding which weights to share between tasks in deep learning models.
method Combines natural evolution strategy and stochastic gradient descent to learn optimal weight sharing.
result Task-specific networks achieve lower test errors than existing methods on multi-task learning datasets.
A new stock selection strategy uses combined machine learning with dynamic weighting methods.
problem Improving stock selection accuracy and performance.
method Combined machine learning algorithms with static and dynamic weighting methods.
result IC-based dynamic weighting outperforms static evaluation metrics in backtested returns and predictive performance.
New method learns to weight unlabeled data in semi-supervised learning.
problem Equal weighting of all unlabeled data in semi-supervised learning.
method Adjust weights for each unlabeled example using influence function.
result Technique outperforms state-of-the-art methods on image and language classification tasks.
A new method to improve deep neural networks using weight rescaling.
problem Overfitting and sensitivity to hyperparameters in weight decay.
method Weight rescaling (WRS) to control weight norm and prevent overfitting.
result WRS outperforms weight decay and other methods in various applications.
New learning process for neural classifiers simplifies decision weights.
problem Training decision layer weights in neural classifiers.
method Choosing appropriate loss functions and solving constrained optimization problems.
result A new learning process for pre-decision weights that is simple and effective.
Improved neural networks by averaging late-stage weights.
problem Improving the performance of neural networks.
method Ensemble late-stage weights and average them.
result Augmenting standard models with late-phase weights improves generalization.
This paper presents a supervised learning algorithm, namely, the Synaptic Efficacy Function with Meta-neuron based learning algorithm (SEF-M) for a spiking neural network with a time-varying weight model. For a given pattern, SEF-M uses the learning algorithm derived from meta-neuron based learning algorithm to determi…
Hardness proven for neural networks with natural weights.
problem Difficulty in learning neural networks with weights from natural distributions.
method Proved hardness for depth-2 networks with natural weights distributions.
result Most networks are hard to learn with natural weights.
HydaLearn dynamically adjusts task weights for better MTL performance.
problem Constant loss weights in MTL lead to poor results due to drifting relevance and varying mini-batch composition.
method HydaLearn uses mini-batch gradients to dynamically adjust task weights.
result HydaLearn improves performance on synthetic and real-world data.
This paper addresses the question of how a previously available control policy πs can be used as a supervisor to more quickly and safely train a new learned control policy πL for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the superv…
A new method uses nearest neighbors for importance weighting.
problem Data covariate shift problems in machine learning.
method Nearest neighbor classification scheme for determining importance weights.
result Demonstrated effectiveness through comparative experiments on various classification tasks.
Extends online learning to metric spaces using exponential weights.
problem Online learning in metric spaces.
method Exponentially weighted average forecaster, barycenters, Jensen's inequality, measure contraction property.
result Results in a statistical learning framework.
The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.
problem Reward modeling in policy optimization and its impact on downstream value.
method Two-stage neural reward model: first learns hidden direction, then fits readout layer.
result For any feature-learning temperature above a dimension-free threshold, a constant fraction of neurons recover the hidden direction.
BetaDataWeighter learns weights for unlabelled data to improve self-supervised learning accuracy.
problem Improving unsupervised representations with domain shift between unlabelled and target data.
method Learning Bayesian instance weights for unlabelled data to prioritize useful instances.
result BetaDataWeighter achieves highest average accuracy and prunes up to 78% of images without significant loss in accuracy.
This paper explores how representation learning can improve design-based causal inference.
problem Estimating causal effects in design-based studies is challenging due to the need for optimal weights.
method The authors propose an end-to-end estimation procedure that learns a flexible representation to minimize the error in choosing a representation.
result The proposed method is competitive in various causal inference tasks and shows promise for improving design-based weights.
SGD and weight decay encourage neural networks to learn low-rank weight matrices.
problem The bias of SGD towards low-rank weight matrices in neural networks.
method The study investigates the effect of SGD and weight decay on the rank of weight matrices in neural networks, both theoretically and empirically.
result Training with SGD and weight decay induces a bias towards rank minimization in weight matrices, which becomes more pronounced with smaller batch sizes and stronger weight decay.
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.
Bayesian weight priors improve neural network learning of identity relations.
problem Neural networks struggle to learn abstract and systematic relations, especially identity relations.
method Extended RBP approach using Bayesian weight priors as a regularization term.
result Bayesian weight priors lead to perfect generalization for identity relations and do not hinder standard neural network learning.
The paper analyzes prediction error in nonstationary settings using weighted risk minimization.
problem Prediction under distribution drift and nonstationary conditions.
method General decomposition of excess risk into learning and drift terms, proving oracle inequalities under mixing conditions.
result Oracle inequalities for the learning error, providing bounds that hold uniformly over arbitrary weight classes.
R-Learning uses inverse-variance weights to estimate treatment effects more accurately.
problem Estimating heterogeneous treatment effects (CATEs) with stable and accurate methods.
method R-Learning with inverse-variance weights (IVWs) for pseudo-outcome regression.
result IVWs improve the stability and accuracy of CATE estimation.
FAWMF adapts weights for implicit feedback recommendation efficiently.
problem Challenges in treating unobserved data as negative in implicit feedback recommendation.
method FAWMF uses a variational auto-encoder with a parameterized neural network to adaptively assign personalized data confidence weights, and fBGD for efficient learning.
result FAWMF and fBGD outperform existing methods in real-world datasets.
We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight vectors instead of scalar weights. We turn the problem of learning RLR to learning these vector-weighted formulae and develop a learning alg…
Machine learning approximates Calabi-Yau Hodge numbers from weight systems.
problem Approximating Hodge numbers of Calabi-Yau manifolds from weight systems.
method Neural networks learned Hodge numbers from weight systems, symbolic regression inspired truncation, and machine learning generated new datasets.
result Approximation provides tight lower bounds and dramatically faster computation.
Two local learning rules are investigated to avoid weight transport in neural networks.
problem Local learning rules that avoid weight transport are unstable and require tuning.
method Investigated two non-local learning rules and a more robust local rule.
result Non-local learning rules match state-of-the-art performance and operate effectively in noisy updates.
Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it…
EWC helps prevent forgetting in neural networks by adjusting weights dynamically.
problem Preventing forgetting in neural networks during training.
method EWC adjusts weights dynamically to prevent forgetting.
result EWC effectively prevents catastrophic forgetting in neural networks.
A new method for offline RL using diffusion models and self-weighted guidance.
problem Challenges in computing scores for offline RL using weight functions.
method Constructing a diffusion over actions and weights, using the diffusion model for guidance.
result Performs on par with state-of-the-art methods on challenging environments.
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
Real-world machine learning applications often have complex test metrics, and may have training and test data that are not identically distributed. Motivated by known connections between complex test metrics and cost-weighted learning, we propose addressing these issues by using a weighted loss function with a standard…
Random feature maps improve forecasting with cheaper computation.
problem Improving forecasting accuracy with random feature maps.
method Developed a hit-and-run algorithm to select optimal internal weights.
result Optimal internal weights lead to superior forecasting skill.
Enhances trading signals using image analysis and weighted moving averages.
problem Improving price trend trading strategies in financial markets.
method Image-induced importance weights applied to weighted moving averages of trading signals.
result Significant enhancement of price trend trading signals with improved portfolio selection.
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from training loss to sample weight, and then iterating between weight recalculating an…
In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document. In tasks characterized by the presence of training data (such as text classifi…
Theory of learning with weight-distribution constraints.
problem Understanding how structure influences function in neural networks.
method Statistical mechanical theory and optimal transport.
result Reduction in capacity due to constrained weight-distribution is related to Wasserstein distance.
We provide rigorous guarantees on learning with the weighted trace-norm under arbitrary sampling distributions. We show that the standard weighted trace-norm might fail when the sampling distribution is not a product distribution (i.e. when row and column indexes are not selected independently), present a corrected var…
LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.
problem Efficient processing of low-rank weight decompositions in large finetuned models.
method Developed symmetry-aware invariant and equivariant LoL models to process LoRA weights.
result LoL models can predict CLIP scores, finetuning data attributes, and accuracy on downstream tasks.
Proposes WM-NMF for better multi-view clustering.
problem Learning multi-view data with unequal view information content.
method Introduces a weighted multi-view NMF algorithm to learn view-specific and observation-specific weights.
result Achieves better clustering performance and handles noisy data.
Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the i…
In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces large bias in tasks with high action dimensions, and bias from clipping makes it di…
New method improves deep RL by combining emphatic weightings with replay data.
problem Improving sample efficiency and scaling model-free RL methods.
method Developed a multi-step emphatic weighting and time-reversed n-step TD learning algorithm. result The new approach reduces variance and provides convergence guarantees.
Improves transfer learning by weighting importance based on test-over-training density.
problem Distribution shift in training and test data.
method Joint and dynamic importance-predictor estimation, causal mechanism transfer.
result Enhanced transfer learning performance in complex, high-dimensional tasks.
Exploiting different representations, or views, of the same object for better clustering has become very popular these days, which is conventionally called multi-view clustering. Generally, it is essential to measure the importance of each individual view, due to some noises, or inherent capacities in description. Many…
Improved random forest models enhance machine learning predictions.
problem Equal weights for random forest base decision trees are not optimal.
method Proposes algorithms to modify weighting strategy of regular random forest.
result Numerical results show significant improvements over regular random forest.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
New algorithm for learning mixtures with mostly uniform weights, improving on previous bounds.
problem Learning mixtures of Gaussians with uniform weights and mostly uniform component weights.
method Statistical Query (SQ) lower bound and quasi-polynomial upper bound for testing.
result Quasi-polynomial upper bound for testing mixtures with mostly uniform weights.