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.

168,695 papers · 148 categories

Trend · papers per month

91183274365 · Jun 202019922001200920172026
48 results for representation degradation

PROTOCOL tackles imbalanced multi-view clustering by enhancing contrastive learning.

problem Class imbalance in real-world multi-view data.
method PROTOCOL uses partial optimal transport to perceive and mitigate imbalance, enhancing contrastive learning.
result PROTOCOL significantly improves clustering performance on imbalanced multi-view data.

Sparse Transformers degrade semantic information first, with early layers encoding more.

problem Understanding how sparse Transformers affect learned representations and semantic information.
method Probed Transformers with progressively pruned weights to observe changes in semantic information and model behavior.
result Complex semantic information is first to degrade in sparse Transformers, with early layers encoding more.

PARIS reduces imbalanced regression datasets by pruning uninformative samples.

problem Imbalanced regression where models focus on high-frequency regions, ignoring rare but impactful events.
method PARIS uses the representer theorem to compute a closed-form representer deletion residual for iterative pruning of the training set.
result PARIS reduces training set by up to 75% while preserving or improving overall performance, outperforming other methods.

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose bl…

2018-03-20abs ↗pdf ↗

Contrastive learning performance doesn't degrade with more negative samples.

problem Theoretical and empirical evidence of negative samples hurting performance in contrastive learning.
method Simple theoretical setting and empirical support on CIFAR-10 and CIFAR-100 datasets.
result Contrastive learning performance does not degrade with the number of negative samples.

Improves performance of deep GCNs by controlling node feature variance.

problem Performance degradation in deep Graph Convolutional Networks (GCNs).
method Experimentally examined the role of TRANs and PROPs in GCNs, introduced Node Normalization (NodeNorm).
result Node Normalization effectively controls node feature variance, improving GCN performance in deep models.

The paper tackles fair representation learning by smoothing feature mappings.

problem Legal liability for discriminatory use of data by organizations.
method Mapping features to a fair representation space, certifying fairness through chi-squared mutual information.
result Smoothing representation distribution provides generalization guarantees of fairness and maintains accuracy for downstream tasks.

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates …

2018-08-07abs ↗pdf ↗

Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a cruc…

2015-02-09abs ↗pdf ↗

A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, t…

2019-12-10abs ↗pdf ↗

CausalCOMRL improves RL task representations by integrating causal relationships, enhancing generalizability.

problem Spurious correlations in context-based offline meta-reinforcement learning.
method CausalCOMRL integrates causal representation learning to uncover and incorporate causal relationships among task components.
result CausalCOMRL achieves better performance on meta-reinforcement learning benchmarks.

Statistical test detects model degradations in optimized language models.

problem Detecting model degradations in optimized language models.
method Statistical hypothesis testing framework based on McNemar's test.
result Even small accuracy degradations (0.3%) can be attributed to actual degradations, not noise.

This paper tackles noise in raw datasets to improve representation learning efficiency.

problem Noise in real-world datasets degrades representation learning quality.
method Proposes denoising Cosine-Similarity (dCS) loss to learn robust representations.
result Empirical results show the dCS loss outperforms baseline objective functions.

Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network to low precision degrades its performance. Crucially, networks that are designed for embedded applications usually suffer from increased de…

2019-06-07abs ↗pdf ↗

Binary representation is desirable for its memory efficiency, computation speed and robustness. In this paper, we propose adjustable bounded rectifiers to learn binary representations for deep neural networks. While hard constraining representations across layers to be binary makes training unreasonably difficult, we s…

2015-11-19abs ↗pdf ↗

BNCR-GAN improves GANs to generate clean images from degraded inputs.

problem Generating clean images from blurred, noisy, and compressed degraded inputs.
method Multiple-generator model with image, blur-kernel, noise, and quality-factor generators, using masking architectures and adaptive consistency losses.
result BNCR-GAN effectively learns clean image generators from degraded images without degradation parameters.

New framework analyzes why more negative samples improve self-supervised learning performance.

problem Inconsistency between theoretical degradation and empirical improvement of downstream supervised tasks with more negative samples.
method Coupon collector's problem framework to analyze self-supervised representation learning with more negative samples.
result Bound can implicitly incorporate supervised loss in self-supervised loss by increasing negative samples.

Neural network predicts electrochemical cell faults with 53% less error.

problem Predicting faults in electrochemical cells to avoid safety hazards and reduce costs.
method Self-supervised encoder-decoder neural network that learns degradation from operating conditions.
result Predicted voltage with 53% less error than parametric models, 64% faster fault prediction.

Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.

problem Intractable computation due to timescale mismatch between battery degradation and market dynamics.
method Approximate dynamic programming with value function approximation and pseudo-time encoding.
result Policy outperforms benchmarks in real-time market scenarios.

TPA-AD detects axle-box bearing anomalies using pseudo anomalies near normal boundaries.

problem Detecting axle-box bearing anomalies with only normal training data.
method Two-stage approach: pseudo anomalies, contrastive learning, KNN.
result Improves anomaly detection separability and sensitivity to degradation.

It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represents the similarity between two points. There are two popular schemes to construct a similarity graph, i.e., pairwise distance based scheme an…

2013-04-24abs ↗pdf ↗

Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.

problem RUL estimation challenges in practice, especially online update and uncertainty quantification.
method Hybrid DNN approach with Wiener-based-degradation model and adaptive drift. LSTM-CNN for trajectory prediction and Bayesian inference for adaptive drift.
result Superior accuracy in RUL prediction demonstrated on turbofan engines data.

A method for inferring ground-truth signals from degraded sensor data.

problem Inferring ground-truth signals from multiple degraded sensor signals.
method Iterative correction of degraded signals using a Bayesian multi-sensor data fusion method.
result The method effectively infers ground-truth signals from noisy and degraded sensor data.

Sparse molecular representations improve interpretability in graph neural networks.

problem Difficulty in understanding which molecular graph aspects drive deep learning predictions.
method Constrain weights in a graph convolutional neural network using the Gini index to maximize representation inequality.
result The Gini-constrained approach does not degrade evaluation metrics and allows for interpretable representation combination.

Empirical mode modeling improves state-space analysis of noisy data.

problem Analyzing nonlinear systems with noisy data.
method Combining empirical mode decomposition with empirical dynamic modeling.
result Empirical mode modeling enhances state-space representations in noisy data.

Universal model for soft tissue mechanics under shock waves.

problem Modeling shock wave mechanics in soft biological tissues.
method Continuum mixture theory with phase-field mechanics.
result Universal thermodynamically consistent formulation for soft porous tissues.

Kernel ridge regression is used to approximate the kinetic energy of non-interacting fermions in a one-dimensional box as a functional of their density. The properties of different kernels and methods of cross-validation are explored, and highly accurate energies are achieved. Accurate {\em constrained optimal densitie…

2014-04-04abs ↗pdf ↗

Paper predicts bearing degradation stages for pharmaceutical industry maintenance.

problem Predicting when to maintain specific parts of production machines.
method AutoEncoder-based k-means segmentation of high-frequency vibration data.
result Framework generates reliable predictions for bearing degradation stages.

Paper proposes a new regularization method to prevent model degradation under distribution shifts.

problem Model performance degrades under distribution shifts.
method Supervised contrastive learning with heterogeneous similarity.
result The proposed method outperforms existing regularization methods on benchmark datasets.

RNNs solve modular addition tasks using low rank and sparse Fourier structures.

problem Solving modular addition tasks with recurrent neural networks.
method Identified low rank structures and sparse Fourier representations in RNN weights.
result RNNs robust to removing individual frequencies but degrade with more ablation.

Theory models nonlinear soft tissue elasticity and remodeling using extended Finsler geometry.

problem Understanding and predicting the behavior of nonlinear soft tissues, especially in biologic contexts.
method Formulated a continuum mechanical theory incorporating extended Finsler geometry to describe the complex behaviors of fibrous soft solids.
result The model quantifies residual strains from growth, remodeling, and degradation, and predicts equilibrium configurations.

Deep RL for portfolio management shows poor robustness.

problem Robustness of Deep RL algorithms in online portfolio management.
method Proposed a training and evaluation process for assessing DRL algorithms.
result Most Deep RL algorithms are not robust, generalizing poorly and degrading quickly.