Fine-grained analysis of gradient descent with momentum provides modified loss equations.
problem Understanding the dynamics of gradient descent with momentum.
method Fine-grained analysis and derivation of modified loss equations.
result Global approximation bounds and continuous modified equations for HB.
Enhances ENet's prediction accuracy while maintaining uncertainty estimation.
problem Gradient shrinkage problem in ENet's loss function.
method Proposes a multi-task learning framework with a modified MSE loss function.
result Improves ENet's prediction accuracy without losing uncertainty estimation.
Fence GAN improves anomaly detection by modifying GAN loss.
problem Anomaly detection on complex high-dimensional data.
method Modified GAN loss to encourage generated samples at the boundary of real data distribution.
result Fence GAN yields the best anomaly classification accuracy.
Modified Jones-Faddy skew t-distribution captures asymmetry in stock returns.
problem Negative skew and positive mean in stock returns due to broken symmetry of stochastic volatility.
method Modified Jones-Faddy skew t-distribution applied to split gains and losses, using stochastic differential equations for stock returns and volatility.
result The modified distribution effectively captures the asymmetry in daily S&P500 returns, including its tails.
We address feature interpretation and reproducibility issues in dense nets, proposing a modified loss function.
problem Feature interpretation and reproducibility issues in dense nets.
method Proposed a modified loss function to circumvent basis collapse.
result Substantially concise nets with 100x fewer parameters and lower MSE loss.
SGD with large learning rates can achieve better test accuracy than expected.
problem SGD with large learning rates often outperforms expected convergence bounds.
method Proved that SGD with small learning rates stays close to gradient flow path on modified loss.
result Explicitly adding an implicit regularizer to the loss improves test accuracy.
New loss function improves convergence rate for neural networks.
problem Improving convergence speed of neural networks for classification tasks.
method Proposes a modified hinge loss function with gradients to critical points.
result Margin converges to max-margin at O(1/t) rate, faster than exponential losses. Paper introduces a new topological loss for better convergence.
problem Optimizing topological losses for model's desired topological behavior.
method Introduces a new regularized topology-aware loss function.
result Guarantees efficient optimization of the new loss function.
Previous research has shown that for stock indices, the most likely time until a return of a particular size has been observed is longer for gains than for losses. We establish that this so-called gain/loss asymmetry is present also for individual stocks and show that the phenomenon is closely linked to the well-known …
Modified AUC improves CNN training by considering model confidence.
problem Improving binary classifier performance metrics.
method Proposes a modified AUC metric that incorporates model confidence into BCE loss for CNN training.
result Demonstrates improved performance on three datasets: MNIST, prostate MRI, and brain MRI.
Data discretization is an important step in the process of machine learning, since it is easier for classifiers to deal with discrete attributes rather than continuous attributes. Over the years, several methods of performing discretization such as Boolean Reasoning, Equal Frequency Binning, Entropy have been proposed,…
NDI aims to forecast future natural disasters risk for insurers.
problem Increasing intensity and frequency of natural disasters.
method Develops a Natural Disasters Index (NDI) based on NOAA data.
result NDI forecasts future natural disasters risk for insurers.
This work provides bounds on the performance of prediction models in the predict-then-optimize framework.
problem Generalizing the performance of prediction models in the predict-then-optimize framework with the SPO loss function.
method Deriving generalization bounds using the Natarajan dimension and exploiting the strength property of the feasible region.
result Improved generalization bounds for the SPO loss function, scaling logarithmically in the number of extreme points and linearly in the decision dimension.
The overarching goal of this paper is to derive excess risk bounds for learning from exp-concave loss functions in passive and sequential learning settings. Exp-concave loss functions encompass several fundamental problems in machine learning such as squared loss in linear regression, logistic loss in classification, a…
The method learns disentangled representations for localized image manipulations.
problem Image generating neural networks are viewed as black boxes with global effects.
method Localized ResNet Autoencoder with multiple loss functions.
result The network can transfer specific facial attributes like shape and color of eyes, hair, mouth, etc. between persons.
Characterizes learnability of forgiving 0-1 loss functions in multiclass settings.
problem Understanding when multiclass learning with forgiving 0-1 loss functions is possible.
method Introduces a new combinatorial dimension based on Natarajan Dimension to determine learnability.
result A hypothesis class is learnable if and only if the Generalized Natarajan Dimension is finite.
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier. Specifically, we introduce the notion of \emph{consistency intensity} to characterize a surrogate loss function and exploit this notion to obtain the rate of convergence from an empirical surrogate risk minimizer…
Label smoothing improves model robustness against misspecification.
problem Improving model robustness against model misspecification.
method Introducing modified label smoothing (MLSLR) that maintains consistent probability estimation while modifying the loss function.
result MLSLR exhibits higher robustness against model misspecification than conventional label smoothing.
In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction…
Introduces Fitzpatrick losses, tighter than Fenchel-Young losses.
problem Improving loss functions for machine learning.
method Introduces Fitzpatrick losses based on the Fitzpatrick function.
result Fitzpatrick losses are tighter than Fenchel-Young losses.
Analyzes multi-day stock returns, showing linear volatility and mean dependence.
problem Linear dependence of volatility and mean in accumulated stock returns.
method Modified Jones-Faddy skew t-distribution analysis.
result Linear dependence of volatility and mean on the number of days of accumulation.
New loss function improves classification accuracy.
problem Negative expected accuracy as an alternative to cross entropy for classification.
method Empirical investigation using modified leaky version of expected accuracy.
result Comparable or better accuracy compared to cross entropy, robust to label noise.
It is known that Boosting can be interpreted as a gradient descent technique to minimize an underlying loss function. Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers. Therefore, several Boosting algorith…
Simplifies risk minimization combining mean and standard deviation.
problem Minimizing mean and standard deviation under heavy-tailed losses.
method Adapting robust mean estimation technique to include standard deviation.
result Simple approach performs as well or better than alternative risk criteria.
DM improves deep model robustness for noisy, imbalanced datasets.
problem Noisy labels and imbalanced datasets in real-world large-scale datasets.
method Derivative Manipulation (DM) approach to example weighting.
result DM enhances robustness of deep models under adverse conditions.
In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and…
Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…
Paper uses CNN to create realistic LiDAR data.
problem Creating high-resolution LiDAR data with missing points.
method Modified per-point loss and perceptual loss applied to generate realistic LiDAR data.
result Significant improvement in geometric and semantic accuracy over traditional methods.
Develops a new density ratio estimator for causal inference.
problem Estimation of density ratio functions in statistics.
method Super learning approach with a novel loss function.
result Empirical validation of the density ratio super learner's performance.
We make three contributions to the theory of k-armed adversarial bandits. First, we prove a first-order bound for a modified variant of the INF strategy by Audibert and Bubeck [2009], without sacrificing worst case optimality or modifying the loss estimators. Second, we provide a variance analysis for algorithms based …
Improved PAC-Bayesian bounds by considering example difficulty.
problem Improving generalization bounds in machine learning.
method Introducing a modified excess risk that leverages example difficulty to reduce variance and tighten PAC-Bayesian bounds.
result Tighter PAC-Bayesian generalization bounds for machine learning models.
This work proposes SDI regularization to improve adversarial robustness.
problem Improving adversarial robustness of deep neural networks.
method SDI regularization term to complement adversarial training.
result Combining SDI with AT variants enhances robustness and generalization.
Develops an empirical likelihood framework for random forests and ensembles.
problem Quantifying the statistical uncertainty of random forests and ensembles.
method Empirical likelihood framework exploiting the incomplete U-statistic structure of ensemble predictions. result Modified empirical likelihood statistic achieves accurate coverage and practical reliability.
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.
A new asymmetric contrastive loss improves performance on imbalanced datasets.
problem Improving performance on imbalanced datasets using contrastive learning.
method Introducing an asymmetric contrastive loss (ACL) and asymmetric focal contrastive loss (AFCL).
result AFCL outperforms CL and FCL in terms of weighted and unweighted classification accuracies on imbalanced datasets.
Anomalous diffusion in SGD reveals interactions between hyperparameters and Hessian.
problem Understanding the limiting dynamics of SGD in deep neural networks.
method Continuous-time model of SGD as an underdamped Langevin equation, derived for linear regression.
result Anomalous diffusion is explained by modified loss and probability currents in phase space.
Improved BN for better performance in imbalanced data.
problem Improving classification accuracy in imbalanced datasets.
method Combining weighted loss function with modified batch normalization.
result Modified batch normalization improves classification accuracy in imbalanced datasets.
New method wraps black-box classifiers to reduce bias.
problem Reduction of bias in black-box predictions.
method Post-processing with α-trees and boosting algorithms.
result Demonstrated effectiveness in reducing bias across multiple fairness metrics.
BCD algorithm finds global minima in neural networks.
problem Training deep neural networks to find global minima.
method Block coordinate descent with skip connections and non-negative projection.
result Proves convergence to global minima for strictly monotonic and ReLU activations.
Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.
problem Understanding the conditions under which gradient descent converges with arbitrary stepsize.
method Using Fenchel-Young losses and leveraging the classical perceptron argument to derive convergence rates.
result GD converges with arbitrary stepsize for a majority of Fenchel-Young losses, with better rates for specific loss functions.
Given a training set with binary classification, the Support Vector Machine identifies the hyperplane maximizing the margin between the two classes of training data. This general formulation is useful in that it can be applied without regard to variance differences between the classes. Ignoring these differences is not…
Enhances graph embeddings by preserving graph topology.
problem Node2vec struggles to recreate the topology of input graphs.
method Introduces a topological loss term to Node2vec, aligning the persistence diagram of the embedding to that of the input graph.
result Reconstructs both geometry and topology of input graphs.
Modified swarm optimizers improve GD initialization for EEG spatial filtering.
problem Gradient Descent fails in complex, multi-scale convexity scenarios.
method Modified Swarm-based Optimizers (ICA and PSO) applied to GD initialization.
result The modified optimizers outperform baseline optimizers in EEG classification and loss function fitness.
Data compression speeds up machine learning loss calculations.
problem Computational demand in calculating mean squared error for large datasets.
method Use rank-1 lattices to compress data, assigning weights based on original data and responses.
result Our QMC data compression algorithms can lead to arbitrary high convergence rates for smooth functions.
Proposes a new regularization technique for neural networks using elliptic operators.
problem Improving model behavior in underrepresented data regions.
method Modifies the empirical risk minimization objective to minimize an elliptic operator over the data domain.
result The proposed regularization technique anticipates error behavior outside the training set using existing elliptic operator theory.
Paper introduces DCoVaR for aggregate risk models, outperforming existing methods.
problem Lack of coherent risk measures for aggregate risk models.
method Proposes Dependent Conditional Value-at-Risk (DCoVaR) for a target loss dependent on another random loss.
result DCoVaR outperforms MCoVaR and CCoVaR in numerical simulations and empirical studies.
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that …
Cautious Weight Decay modifies weight decay for better optimization.
problem Improving optimization in deep learning models.
method Applies weight decay selectively based on parameter sign alignment.
result Consistently improves model performance across various tasks and scales.