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…
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.
168,932 papers · 148 categories
Trend · papers per month
48 results for “importance weights avoidance”
DualDICE estimates discounted distribution ratios for reinforcement learning datasets.
problem Accurate estimation of discounted stationary distribution ratios for reinforcement learning applications.
method Behavior-agnostic algorithm that avoids importance weights and is theoretically guaranteed.
result Significantly improves off-policy policy evaluation accuracy compared to existing techniques.
New method evaluates policies with latent confounders using optimal balance.
problem Evaluating policies with unobserved confounders in costly exploration scenarios.
method Importance weighting method to avoid latent outcome regression, minimizing adversarial balance objective.
result Provable consistency in policy evaluation with latent confounders, demonstrated empirically.
A new resampling strategy, Importance Resampling, improves sample efficiency and reduces variance in off-policy prediction.
problem High variance updates in importance sampling for off-policy prediction.
method Importance Resampling (IR) resamples experience from a replay buffer and applies standard on-policy updates, avoiding importance sampling ratios.
result Importance Resampling (IR) shows improved sample efficiency and lower variance updates compared to other methods.
Paper proposes a new strategy to improve initial performance of federated models.
problem Weight divergence in Federated Averaging (FedAvg) leads to poor initial performance in federated models.
method Local continual training with importance weights evaluated on a proxy dataset.
result The method significantly improves the initial performance of federated models with minimal extra communication costs.
A method for optimal Bayesian filtering using progressive particle flow and optimal transport maps.
problem Optimizing Bayesian filtering with deterministic particles to avoid degeneration.
method Progressive flow of particles through a sequence of sub-steps, each using an optimal transport map to replace non-equally weighted particles with equally weighted ones.
result The method avoids particle degeneration and simplifies the filtering process by not requiring inversions or monotonicity constraints.
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller target subnetwork. We propose a new method for compute-constrained structured channe…
Estimates LATE using combined datasets, overcoming data limitations.
problem Estimating LATE when compliance is incomplete and data is split.
method Combines separately observed datasets to estimate LATE using direct and weighted least squares methods.
result Proposes a stable and practical estimator for LATE.
Proposes SOVR loss to improve adversarial robustness by increasing logit margins.
problem Adversarial training's difficulty in robustness against sophisticated attacks.
method Introduces SOVR loss function that switches from cross-entropy to one-vs-the-rest loss for important samples.
result SOVR loss increases logit margins of important samples, improving robustness against Auto-Attack.
A Frobenius norm regularization method for convolutional kernels to avoid unstable gradient problemcs.LG
New method bounds singular values of convolutional kernels to stabilize gradients.
problem Stable gradients in convolutional neural networks.
method Frobenius norm regularization for convolutional kernels.
result Bounded singular values of transformation matrices.
R2D2-Net improves Bayesian neural networks by preventing over-shrinkage of important weights.
problem Bayesian neural networks struggle with choosing appropriate priors, leading to over-shrinkage or poor predictive performance.
method Proposes R2D2-Net with an R^2-induced Dirichlet Decomposition prior and variational Gibbs inference algorithm.
result R2D2-Net effectively shrinks irrelevant coefficients while preventing key features from over-shrinkage.
A new algorithm flattens multi-modal distributions for better deep learning.
problem Bayesian learning in big data with multi-modal distributions.
method Contour Stochastic Gradient Langevin Dynamics (CSGLD) algorithm.
result The CSGLD algorithm avoids local traps in deep neural networks.
New algorithm provably converges to second-order stationary points in NMF.
problem Understanding convergence to local minima in NMF.
method Multiplicative weight update dynamics, concurrent updates, and simplex reduction.
result Provable convergence to second-order stationary points.
AISLE framework improves on IWAE by directly optimising proposal distribution.
problem IWAE's multi-sample objective leads to inference-network gradients that break down with increasing samples.
method Introduces AISLE framework, which optimises proposal distribution directly.
result AISLE admits IWAE-STL and IWAE-DREG as special cases, avoiding breakdown.
Shortcut connections in ResNet help avoid local optima, leading to efficient training.
problem Understanding why shortcut connections in ResNet lead to efficient training.
method Two-layer non-overlapping convolutional ResNet, gradient descent with proper normalization.
result Gradient descent avoids spurious local optima, converging to a global optimum.
Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, h…
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.
New method prevents deep learning forgetting past by remembering key examples.
problem Catastrophic forgetting in continual learning.
method Functional regularisation using Gaussian Process formulation.
result Achieves state-of-the-art performance on benchmarks.
New methods combine model predictions to avoid linear mixtures' limitations.
problem Combining predictions from different models to avoid linear mixtures' limitations.
method Log-linear pooling (locking) and quantum superposition (quacking) to optimise model weights.
result Demonstrated locking method with illustrative example and practical application.
Hybrid regularization avoids double descent in random feature models.
problem Avoiding the double descent phenomenon in random feature models.
method Combines early stopping and weight decay, using GCV for hyperparameter selection.
result Hybrid method successfully avoids double descent and achieves comparable generalization.
New method for initializing networks robustly, improving performance across various settings.
problem Insufficient initialization strategies for weight-normalized networks and ResNets.
method Proposes a novel initialization strategy based on mean field approximation.
result Improves generalization performance and robustness to hyper-parameters.
We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode, exploding/vanishing mean activation length, can be avoided by initializing weights from a …
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.
S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minimacs.LG
S-SGD adds symmetrical noise to weights to avoid sharp minima in deep learning.
problem SGD does not always converge to a flat minimum, leading to poor generalization.
method Symmetrical weight noise injection in SGD.
result S-SGD outperforms conventional SGD and weight-noise injection methods in large batch training.
The Zone of Avoidance makes it difficult for astronomers to catalogue galaxies at low latitudes to our galactic plane due to high star densities and extinction. However, having a complete sky map of galaxies is important in a number of fields of research in astronomy. There are many unclassified sources of light in the…
Anomaly detecting as an important technical in cloud computing is applied to support smooth running of the cloud platform. Traditional detecting methods based on statistic, analysis, etc. lead to the high false-alarm rate due to non-adaptive and sensitive parameters setting. We presented an online model for anomaly det…
Deep equilibrium models converge globally without explicit computation.
problem Global convergence of deep learning models with implicit layers.
method Analysis of gradient dynamics and proof of convergence rate.
result Deep equilibrium models converge to global optimum at a linear rate.
New loss function restores importance weighting in overparameterized models.
problem Restoring importance weighting in overparameterized neural networks.
method Introduced polynomially-tailed losses to restore effects of importance weighting.
result Polynomially-tailed losses improve performance in correcting distribution shift.
New methods reduce extrapolation errors in feature importance.
problem Flawed feature importance methods using unrestricted permutations lead to extrapolation errors.
method Three new approaches: conditional model reliance, Knockoffs with Gaussian transformation, and restricted ALE plot designs.
result Theoretical and numerical results show our strategies reduce/eliminate extrapolation.
Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding gradients. In this paper, simplified models of ResNets are analyzed. We argue that good…
New algorithm improves accuracy of importance weights for diverse applications.
problem Improving accuracy of importance weights for various applications.
method Formulated multicalibrated partitions and developed an efficient algorithm.
result Algorithm significantly improves accuracy of importance weights.
Cross-validation under sample selection bias can, in principle, be done by importance-weighting the empirical risk. However, the importance-weighted risk estimator produces sub-optimal hyperparameter estimates in problem settings where large weights arise with high probability. We study its sampling variance as a funct…
Coupling the reduced-order model and the generative model for an importance sampling estimatorstat.ML
In this work, we develop an importance sampling estimator by coupling the reduced-order model and the generative model in a problem setting of uncertainty quantification. The target is to estimate the probability that the quantity of interest (QoI) in a complex system is beyond a given threshold. To avoid the prohibiti…
Complex-valued neural networks avoid spurious local minima.
problem Finding spurious local minima in neural networks.
method Proved no spurious local minima for shallow complex neural networks with quadratic activations.
result Complex-valued weights eliminate spurious local minima in neural networks.
Diversifying an Indexq-fin.PM
A new index rebalancing strategy reduces large constituent weights without undesirable effects.
problem Undesirable effects of current Nasdaq-100 index rebalancing.
method A simple rebalancing strategy that avoids undesirable effects.
result Preserves the order of index weights and prevents maximum weight increase.
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…
Membership in the Russell 1000 and 2000 Indices is based on a ranking of market capitalization in May. Each index is separately value weighted such that firms just inside the Russell 2000 are comparable in size to firms just outside (i.e. at the bottom of the Russell 1000) but have much higher index weights. These feat…
Improved neural spike inference from calcium imaging data.
problem Neural spike inference from calcium imaging data.
method Importance weighted adversarial variational autoencoders (IWAE) with adversarial training.
result Adversarial IWAE methods outperform VAEs in inferring neural spikes.
Importance-weighting is a popular and well-researched technique for dealing with sample selection bias and covariate shift. It has desirable characteristics such as unbiasedness, consistency and low computational complexity. However, weighting can have a detrimental effect on an estimator as well. In this work, we empi…
Optimizes weights for better model performance in shifting data.
problem Improper importance weighting leads to poor model performance in data shifts.
method Interprets weights as a bias-variance trade-off and optimizes them simultaneously with model parameters.
result Optimizing weights significantly improves model generalization performance.
CR-AIS improves AIS efficiency by constant rate annealing.
problem Efficiently sample from intractable distributions.
method Constant rate annealing schedule for AIS.
result CR-AIS outperforms existing Adaptive AIS methods.
Flow AIS Bootstrap improves flow training by generating samples in hard-to-reach regions.
problem Training flows with high variance and mode-seeking behavior.
method Augment flows with AIS and minimize -divergence with .
result FAB learns Boltzmann distribution of alanine dipeptide without MD samples.
Increasingly, Internet of Things (IoT) domains, such as sensor networks, smart cities, and social networks, generate vast amounts of data. Such data are not only unbounded and rapidly evolving. Rather, the content thereof dynamically evolves over time, often in unforeseen ways. These variations are due to so-called con…
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.
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.
Sharp analysis of out-of-distribution error in overparameterized models with importance weights.
problem Understanding and quantifying the degradation of performance in overparameterized models when faced with underrepresented data.
method Sharp analysis of an overparameterized Gaussian mixture model with spurious features and cost-sensitive interpolating solutions incorporating importance weights.
result Characterization of a novel tradeoff between worst-case robustness and average accuracy as a function of importance weight magnitude.
This paper compares gradient estimators in importance-weighted VI and justifies the superiority of DREP over REP.
problem Understanding the impact of gradient estimators on importance-weighted VI algorithms.
method Unified theoretical comparison of reparameterized and doubly-reparameterized gradient estimators tied to IWAE, VR, and VR-IWAE bounds.
result Formally justifies the superiority of doubly-reparameterized gradient estimators over reparameterized ones in importance-weighted VI.
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.