Research
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.

169,051 papers · 148 categories

Trend · papers per month

68135203270 · Jun 202019922001200920182026
48 results for weight modification

A new method improves continual learning by replaying pseudo data and using orthogonal weight modification.

problem Catastrophic forgetting in class incremental learning.
method Generative replay with orthogonal weight modification.
result Our method achieves substantial improvement over conventional generative replay and OWM.

The paper introduces a limit version of multiple stopping options such that the holder selects dynamically a weight function that control the distribution of the payments (benefits) over time. In applications for commodities and energy trading, a control process can represent the quantity that can be purchased by a fix…

2010-12-07abs ↗pdf ↗

DeepDiff predicts differential gene expression from histone modifications using deep learning.

problem Predicting differential gene expression from histone modification signals, capturing combinatorial effects.
method Attention-based deep learning architecture with multiple LSTM modules and attention mechanisms.
result DeepDiff significantly outperforms state-of-the-art baselines for differential gene expression prediction.

Pulling back the weight system associated with the exceptional Lie algebra G_2 by a modification of the universal Vassiliev-Kontsevich invariant yields a link invariant; extending it to 3-nets, we derive a recursive algorithm for its evaluation.

1998-06-24abs ↗pdf ↗

The local linear embedding algorithm (LLE) is a non-linear dimension-reducing technique, widely used due to its computational simplicity and intuitive approach. LLE first linearly reconstructs each input point from its nearest neighbors and then preserves these neighborhood relations in the low-dimensional embedding. W…

2008-08-06abs ↗pdf ↗

ModHiFi identifies critical components for model modification without gradients or loss function.

problem Modifying open weight models without access to training data or loss function.
method Theoretical analysis of Lipschitz-continuous networks, Subset Fidelity metric, and ModHiFi algorithm.
result ModHiFi-P and ModHiFi-U achieve significant performance improvements in model pruning and unlearning.

Improves random survival forest model by weighted averaging.

problem Improving the performance of random survival forest.
method Modifies random forest by weighted averaging of trees, optimizing weights via quadratic optimization to maximize Harrell's C-index.
result The weighted random survival forest outperforms the original model in numerical examples.

Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition function. In this way one has to resort to approximation schemes for the evaluation of the gradient.…

2018-01-08abs ↗pdf ↗

Post-training quantization saves resources for neural networks.

problem Implementing neural networks in resource-constrained hardware.
method Generalized post-training quantization method (GPFQ) with modifications for sparsity and error analysis.
result Error decays linearly with over-parametrization, showing minor loss of accuracy.

New algorithms avoid weight transport, outperforming current deep learning methods.

problem Current deep learning algorithms rely on weight transport, which is biologically implausible.
method Two mechanisms: weight mirror and modified Kolen-Pollack algorithm, using random feedback weights.
result These mechanisms outperform feedback alignment and other methods on visual recognition tasks.

Uniform estimates for elliptic problems near polygonal domains.

problem Proving uniform solvability estimates for elliptic problems near polygonal domains.
method Suitable conformal modification of the metric to make the union of domains a manifold with boundary and relative bounded geometry.
result Rounding off the corners of the limit polygonal domain.

Recent breakthroughs in computer vision make use of large deep neural networks, utilizing the substantial speedup offered by GPUs. For applications running on limited hardware, however, high precision real-time processing can still be a challenge. One approach to solving this problem is training networks with binary or…

2017-10-21abs ↗pdf ↗

MCD automates counterfactual design searches for multi-modal tasks.

problem Designing for multi-objective goals and complex constraints.
method Model-agnostic counterfactual search method for multi-modal design modifications.
result MCD streamlines and automates counterfactual search, recommending effective design modifications.

The purpose of this paper is twofold. On one hand, we introduce a modification of the dual canonical basis for invariant tensors of the 3-dimensional irreducible representation of Uq(sl2)U_q(sl_2), given in terms of Jacobi diagrams, a central tool in quantum topology. On the other hand, we use this modified basis to study t…

2015-07-16abs ↗pdf ↗

New methods protect malware classification networks from adversarial attacks.

problem Adversarial perturbations compromise malware classification networks.
method Training restricted networks with non-negative weight restrictions and relaxing constraints.
result Improved classifier accuracy while maintaining resistance to adversarial attacks.

We analyze a negative-parameter variant of the diversity-weighted portfolio studied by Fernholz, Karatzas, and Kardaras (Finance Stoch 9(1):1-27, 2005), which invests in each company a fraction of wealth inversely proportional to the company's market weight (the ratio of its capitalization to that of the entire market)…

2015-04-04abs ↗pdf ↗

Approves updates to machine learning models in healthcare based on accumulating data.

problem Designing policies to autonomously approve updates to machine learning algorithms in non-stationary settings.
method Learning-to-approve (L2A) approach that uses accumulating monitoring data to learn how to approve modifications.
result L2A learns to abstain when performance drops are common and approves beneficial modifications quickly when the distribution is stable.

A simple modification enables a universal NMT model with language-specific parameters.

problem Creating a universal NMT model that can adapt to different languages and domains.
method Introducing a contextual parameter generator (CPG) that dynamically adjusts model parameters based on source and target language embeddings.
result The system achieves state-of-the-art performance and zero-shot translation, demonstrating the effectiveness of the CPG.

Study resolves polynomial germs, proving no mixed critical points and strict transform properties.

problem Resolving mixed critical points and properties of strict transforms of polynomial germs.
method Toric resolutions and modifications of weighted homogeneous polynomials.
result No mixed critical points and strict transform properties as germs.

MimosaNet prevents model stealing by making neural networks sensitive to weight changes.

problem Neural networks are vulnerable to model stealing due to robustness to minor parameter changes.
method Develops a method to create a sensitive version of a trained neural network.
result The sensitive network produces the same responses but is highly sensitive to weight changes, preventing model stealing.

Study shows refugee matching gains are robust to different evaluation methods.

problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.

A simple method to prevent forgetting in neural networks.

problem Catastrophic forgetting in neural networks.
method Weight friction, inspired by neurology and physics, modifies the gradient descent update rule.
result Weight friction enables continual learning with comparable performance and efficiency.

A Siamese Deep Forest (SDF) is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. It can be also regarded as an alternative to the well-known Siamese neural networks. The SDF uses a modified training set consisting of concatenated pa…

2017-04-27abs ↗pdf ↗

Researchers extend period maps for Calabi-Yau types using modified Kato-Nakayama-Usui construction.

problem Existence of weak fans for non-classical period maps of weight 3 Calabi-Yau type.
method Modified Kato-Nakayama-Usui construction for period maps of weight 3 Calabi-Yau type.
result Existence of weak fans for a large class of period maps of weight 3 Calabi-Yau type.

New method improves deep learning performance without weight symmetry.

problem Challenges in scaling non-symmetric learning methods to deep convolutional networks.
method Introduced techniques to mitigate scalability issues, including a modified feedback alignment method.
result Demonstrated competitive performance with backpropagation using a weaker form of weight symmetry.

ZeroS improves Transformers by adding negative weights, matching or beating softmax attention.

problem Limited performance of linear attention methods, especially in long context sequences.
method Proposes Zero-Sum Linear Attention (ZeroS) that removes the zero-order term and reweights zero-sum softmax residuals.
result ZeroS matches or exceeds standard softmax attention across various benchmarks, theoretically expanding representable functions.

Selecting important features in non-linear or kernel spaces is a difficult challenge in both classification and regression problems. When many of the features are irrelevant, kernel methods such as the support vector machine and kernel ridge regression can sometimes perform poorly. We propose weighting the features wit…

2009-06-24abs ↗pdf ↗

This work improves testing of machine learning model modifications using novel statistical methods.

problem Overfitting and conservative Bonferroni correction when testing multiple model modifications.
method Introduces alpha-recycling and SRGPs to control error rate and approve more beneficial modifications.
result Novel statistical methods approve a higher number of beneficial modifications than previous approaches.

Shared Keyboard design improves phase I clinical trials by borrowing information across doses.

problem Interim decisions based on current dose data may overlook signals from neighboring doses.
method Bayesian model-assisted design using Beta kernel process with kernel-weighted pseudo-counts.
result Significant improvements in identifying maximum tolerated dose and safety.

A new method improves cross-domain sentiment analysis by learning weighted domain-invariant representations.

problem Label distribution changes across domains harm domain adaptation in DIRL.
method Proposes WDIRL, a modification to DIRL that learns weighted domain-invariant representations.
result Empirical studies show the effectiveness of WDIRL in cross-domain sentiment analysis.

A Discriminative Deep Forest (DisDF) as a metric learning algorithm is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. The case of the fully supervised learning is studied when the class labels of individual training examples are …

2017-05-25abs ↗pdf ↗