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…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “large weights”
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…
SWAP uses large mini-batches to train DNNs faster with good generalization.
problem Training deep neural networks with small mini-batches is time-consuming.
method SWAP computes an approximate solution with large mini-batches and refines it by averaging weights of multiple parallel models.
result SWAP trains models as well as small-batch training but in significantly less time.
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.
Adversarial robustness improved by sparsity in network weights.
problem How sparsity affects adversarial robustness in neural networks.
method Theoretical proof and experimental validation of adversarial pruning methods.
result Weights sparsity improves adversarial robustness, especially through inheritance from smaller networks.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
problem Training large models requires memory beyond single accelerator capacity.
method Pipeline parallelism, weight gradient coalescing, double buffering.
result Accelerates large model training by up to 20x.
This paper analyzes convergence of large-scale Transformers with weight decay.
problem Understanding optimization guarantees in large-scale Transformer training.
method Construct mean-field limit, show gradient flow convergence to PDE, demonstrate global minimum consistency.
result Gradient flow reaches global minimum in large-scale Transformers with small weight decay.
LAWN normalizes logits to improve deep network adaptability and generalization.
problem Large logits and weights lead to overfitting in deep networks.
method Logit Attenuating Weight Normalization (LAWN) constrains weight norms in the final sub-network.
result LAWN improves generalization and adaptability of deep networks.
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Modelscs.LG
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.
Paper proposes a new activation function to reduce overfitting and large weight update issues.
problem Overfitting and large weight update problems in neural networks.
method Introduces a new activation function called Thresholded Exponential Rectified Linear Units (TERELU).
result TERELU shows better performance in reducing overfitting and large weight update issues compared to other activation functions.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
Water pollution is a major global environmental problem, and it poses a great environmental risk to public health and biological diversity. This work is motivated by assessing the potential environmental threat of coal mining through increased sulfate concentrations in river networks, which do not belong to any simple …
Combines VaR and ES forecasts from a large pool of methods.
problem Combining forecasts from a large pool of VaR and ES methods.
method Adapted interval forecast combination methods, including trimmed means and mixtures approach.
result Trimmed mean combinations, mixtures method, and performance-based weighting delivered strong results.
Improved LLM pre-training performance through better weight and variance control.
problem Improper weight and variance control in LLM pre-training affects downstream task performance.
method Introduced Layer Index Rescaling (LIR) and Target Variance Rescaling (TVR) techniques.
result Substantial improvements in downstream task performance (up to 4.6%) and reduced extreme activation values.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
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.
Researchers develop method to protect against 'weight poisoning' attacks on pre-trained models.
problem The security threat of downloading untrusted pre-trained weights that can be manipulated after fine-tuning.
method RIPPLe regularization method and Embedding Surgery initialization procedure.
result Demonstrated that weight poisoning attacks are possible even with limited knowledge of the dataset and fine-tuning procedure.
Lower bounds for delta invariant of weighted hypersurfaces proved for K-stability.
problem Proving K-stability of weighted hypersurfaces.
method Abban-Zhuang method and study of linear systems on flags of weighted hypersurfaces.
result Proves K-stability of a large class of quasi-smooth Fano hypersurfaces and all smooth Fano weighted hypersurfaces.
The paper examines the unexpected losses and risk ratios for co-monotonic alternatives in large portfolios.
problem Understanding the unexpected losses and risk ratios for large portfolios with co-monotonic alternatives.
method Analyzes the asymptotic behavior of unexpected losses and risk ratios for co-monotonic alternatives using monotone cash-additive risk measures and Choquet insurance premia.
result Unexpected losses of large weighted portfolios are of order , where is the average weight.
Paper proposes CounterSample to improve convergence in LTR models.
problem Large variance in IPS weights slows convergence in LTR models.
method Introduces CounterSample algorithm with provably better convergence.
result CounterSample converges faster than standard IPS-weighted methods.
The study introduces anytime learning schedules for large language models without fixed horizons.
problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.
Automates debiasing for large language model evaluations through Fisher random walk.
problem Rigorous and scalable evaluation of large language models.
method Semiparametric efficient estimator using Fisher random walk for weighted residual balancing.
result Efficient estimation of contextual preference scores for large language models.
New method corrects quantization errors in LLMs using low-rank matrices.
problem Correcting quantization errors in large language models.
method Introducing low-rank weight matrices to correct quantized activations in LLMs.
result Reduces accuracy gap with original model by more than 50% using low-rank matrices.
New methods for estimating causal effects with limited overlap, using Stable Probability Weighting.
problem Estimating causal effects with limited overlap in multivalued treatments.
method Stable Probability Weighting (SPW) and Finite-Sample Stable Probability Weighting (FPW) methods.
result SPW and FPW provide practical solutions for estimating and inferring causal effects with limited overlap.
New framework reduces LLM complexity by directly finetuning in Boolean domain.
problem Reducing the complexity of large language models (LLMs) while maintaining performance.
method Proposes a novel framework using multi-kernel Boolean parameters for direct finetuning in the Boolean domain.
result Significantly reduces complexity during both finetuning and inference, outperforming recent techniques.
New nonparametric estimators improve causal effect estimation.
problem Estimation of causal effects with selection bias.
method Undersmoothing of the highly adaptive lasso for estimating the weighting mechanism.
result Asymptotic efficiency and convergence to nonparametric efficiency bound.
Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the examples in a mini-batch typically share the same weight perturbation, thereby limi…
The paper proposes a new method for covariate balancing using IPM to improve causal inference.
problem Covariate imbalance in causal inference weighting methods, especially when models are not correctly specified.
method The integral probability metric (IPM) is used to determine optimal weights for treated and control groups.
result The proposed method can be consistent without specifying either the propensity score or outcome regression model.
We consider a problem of manifold estimation from noisy observations. Many manifold learning procedures locally approximate a manifold by a weighted average over a small neighborhood. However, in the presence of large noise, the assigned weights become so corrupted that the averaged estimate shows very poor performance…
This paper optimizes deep learning training by efficiently sharding weight updates across replicas.
problem Redundant weight update computation on all replicas in data-parallel training.
method Automatic sharding of weight updates using static analysis and transformations on the training graph.
result Substantial speedups achieved on large-scale models using Cloud TPUs.
Importance sampling has become an important tool for the computation of tail-based risk measures. Since such quantities are often determined mainly by rare events standard Monte Carlo can be inefficient and importance sampling provides a way to speed up computations. This paper considers moderate deviations for the wei…
The paper identifies five extreme learning regimes for large linear autoencoders.
problem Understanding the learning dynamics of large weight-tied linear autoencoders.
method Formal loss-expansion hierarchy and analysis of gradient flow.
result Five extreme regimes associated with faces of a triangular prism.
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…
Proposes stabilized weights for causal inference using isotonic calibration.
problem Stability and bias issues in inverse propensity weighting.
method Post-hoc isotonic calibration of inverse propensity weights.
result Improves performance of doubly robust estimators of average treatment effect.
LGV boosts adversarial attacks by improving surrogate models.
problem Improving the transferability of black-box adversarial attacks.
method LGV uses a pretrained surrogate model and multiple weight sets from additional training epochs to generate an effective surrogate ensemble.
result LGV outperforms other test-time transformations by significant margins.
Pion optimizes LLMs by preserving weight matrix singular values.
problem Training large language models (LLMs) with standard optimizers leads to unstable weight matrices.
method Pion uses orthogonal transformations to update weight matrices, preserving their singular values.
result Pion offers a stable alternative to standard optimizers for LLM pretraining and finetuning.
We compress large neural networks for quick adaptation to specific contexts.
problem How to quickly adapt a pretrained large neural network to specific contexts.
method Propose a Bayesian hypernetwork framework to compress the network and encourage sparsity.
result Generated compressed networks are significantly smaller than baseline methods.
Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to ob…
The paper studies topological properties of Ricci shrinkers using weighted cohomology.
problem Proving topological results for smooth gradient Ricci shrinkers.
method Weighted cohomology and extensions to mean curvature flow self-shrinkers.
result Establishes upper bounds for Betti numbers, vanishing theorem for cohomology, and dichotomy for ends.
BLAST optimizes deep model inference by learning efficient matrix structures.
problem Efficient inference of large-scale deep neural networks.
method Introduces BLAST matrix for adaptive structured weights.
result Significant compression and performance improvements for various model sizes.
We present a Bayesian formulation of weighted stochastic block models that can be used to infer the large-scale modular structure of weighted networks, including their hierarchical organization. Our method is nonparametric, and thus does not require the prior knowledge of the number of groups or other dimensions of the…
We give an explicit algorithm and source code for combining alpha streams via bounded regression. In practical applications typically there is insufficient history to compute a sample covariance matrix (SCM) for a large number of alphas. To compute alpha allocation weights, one then resorts to (weighted) regression ove…
Path weighting sensitivitiesmath.PR
The paper calculates sensitivities for financial derivatives using path weighting methods.
problem Computing sensitivities for path-dependent financial derivatives with high variance and degeneracy issues.
method Proposes explicit path weighting formula, variance reduction adjustment, and covariance inflation technique.
result Effective methods to address high variance and degeneracy in sensitivities computation.
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…
SWEEN improves certified robustness via weighted ensembling of smoothed classifiers.
problem Finding optimal base classifiers for randomized smoothing.
method Smoothed WEighted ENsembling (SWEEN) scheme.
result SWEEN achieves optimal certified robustness under mild assumptions.
New covariance estimator for financial portfolios.
problem Estimating large financial covariances in non-stationary environments.
method Exponentially weighted averages and cross-validation for nonlinearly shrinking sample eigenvalues.
result Our estimator performs well in large dimensions compared to existing estimators.
Weight Squeezing transfers knowledge from large models to smaller ones, improving performance and speed.
problem Transfer learning and model compression for faster and more efficient training.
method Reparameterization of weights from a large model to a smaller one.
result Weight Squeezing outperforms other methods on GLUE benchmark with faster training.
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.