QLSTM outperforms LSTM in predicting KSE 100 index movements.
problem Predicting stock market movement in uncertain economic conditions.
method Used LSTM and QLSTM models on monthly data of economic indicators.
result QLSTM provided more accurate predictions of KSE 100 index values.
The study analyzes stock price dynamics of S&P 100 using 250k data points.
problem Characterize investor behavior and price dynamics in S&P 100 stocks.
method Two-way fixed-effects model applied to 250k data points of S&P 100 stocks.
result Uncovered nonlinear relationship between return and trend, quantifying trader motivations.
Compact method proves Brown-York mass positivity and connects to major conjectures.
problem Proving positivity of Brown-York's mass and its connections to conjectures.
method Compact approach to proving mass positivity and exploring connections.
result Proved the positivity of Brown-York's mass and its relation to conjectures.
The κ-generalised distribution fits daily stock returns well.
problem Stock returns are often heavy-tailed, not normally distributed.
method Used the κ-generalised distribution with a Monte-Carlo goodness of fit test. result The κ-generalised distribution fits historic daily stock returns well for a significant proportion of analyzed stocks. Persistence is studied in a financial context by mapping the time evolution of the values of the shares quoted on the London Financial Times Stock Exchange 100 index (FTSE 100) onto Ising spins. By following the time dependence of the spins, we find evidence for power law decay of the proportion of shares that remain e…
Study interprets neural network generalization and memorization on corrupted data.
problem Understanding when a neural network has memorized corrupted data versus learned the underlying rule.
method Analyzes multi-layer perceptrons and Transformers on modular arithmetic tasks with corrupted labels.
result Regularization methods can force networks to ignore corrupted data, improving accuracy on uncorrupted data.
Clarifies the confidence interval approach for bioequivalence testing.
problem Ensuring the reliability of bioequivalence testing methods.
method Clarifies the conditions under which a 100(1-2α)% confidence interval yields a size-α test.
result A 100(1-2α)% confidence interval approach for bioequivalence testing yields a size-α test only when the two one-sided tests are 'equal-tailed'.
Goldilocks activation functions improve neural network performance.
problem Improving neural network performance and understanding signal transformation.
method Introducing Goldilocks activation functions that locally deform input signals.
result Goldilocks networks outperform or match SELU and RELU on CIFAR-10 and CIFAR-100 datasets.
SRS improves deep learning accuracy on small image datasets.
problem Training deep neural networks with limited images per class.
method Fixed sequence index sampling with batch replacement.
result Significantly improved classification accuracy on CIFAR-100.
We propose a novel investment decision strategy (IDS) based on deep learning. The performance of many IDSs is affected by stock similarity. Most existing stock similarity measurements have the problems: (a) The linear nature of many measurements cannot capture nonlinear stock dynamics; (b) The estimation of many simila…
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.
The paper solves portfolio liquidation under transient price impact for 100 NASDAQ stocks.
problem Determining optimal trading strategies under various market impact models.
method Derives explicit solutions for market impact parameters in a portfolio liquidation model.
result The derived strategy achieves significant cost savings compared to benchmark models.
Empirical study on adversarial robustness in transfer learning from CIFAR 100 to CIFAR 10.
problem Evaluating adversarial robustness in transfer learning from CIFAR 100 to CIFAR 10.
method Study of adversarial robustness under transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10, using robust optimisation.
result Using PGD examples during training on the source task leads to more general robust features that are easier to transfer and achieve 5.2% more accuracy against white-box PGD attacks.
Res-SE-Net boosts Resnet performance by enhancing bridge-connections.
problem Reduced accuracy in Resnet due to lack of feature map contribution from bridge-connections.
method Proposed Res-SE-Net architecture with Squeeze-and-Excitation (SE) block to quantify and weight feature map importance.
result Res-SE-Net generalizes better than Resnet and SE-Resnet on CIFAR-10 and CIFAR-100 datasets.
The paper calibrates uncertainty in dropout variational inference models.
problem Miscalibration of model uncertainty in dropout variational inference.
method Logit scaling methods are extended to recalibrate model uncertainty.
result Logit scaling reduces miscalibration, improving reliability of predictions.
Convolutional DKMs improve kernel methods on MNIST, CIFAR-10, and CIFAR-100.
problem Improving kernel methods for image classification.
method Developed a novel inter-domain inducing point approximation and introduced various techniques to extend DKMs to convolutional networks.
result Achieved state-of-the-art performance on image classification benchmarks.
This paper examines how to calibrate ensemble members for better prediction accuracy.
problem Improper calibration of deep neural networks leads to unreliable probability estimates.
method Theoretical analysis and empirical evaluation on CIFAR-100 dataset.
result Well-calibrated ensemble members do not guarantee a well-calibrated ensemble prediction, but a well-calibrated ensemble prediction cannot exceed the average performance of its members.
CutMix training technique improves spatial locality in Vision Transformers.
problem Improving spatial locality in Vision Transformers trained from scratch.
method Comparison of Baseline and Modern training protocols on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
result CutMix training component significantly reduces Mean Attention Distance (MAD) in early layers of Vision Transformers.
A restricted Boltzmann machine (RBM) is a generative neural-network model with many novel applications such as collaborative filtering and acoustic modeling. An RBM lacks the capacity to retain memory, making it inappropriate for dynamic data modeling as in time-series analysis. In this paper we address this issue by p…
A framework for multi-label sentiment analysis in 100 languages with dynamic weighting.
problem Cross-lingual sentiment analysis in multi-label settings with label imbalance.
method Dynamic weighting method, focal loss adaptation, optimal class-specific thresholds.
result State-of-the-art performance in 7 out of 9 metrics across 3 languages.
New approach reduces malware detection memory requirements and speeds up training.
problem Efficiently classifying long sequences of malware detection data.
method Developed a new temporal max pooling method and global channel gating design.
result 116x more memory efficient and 25.8x faster training on original dataset.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
A network architecture improves classification performance on various datasets.
problem Improving classification performance on diverse datasets.
method Divide fully connected layer into three levels, learn existing layers, cluster similar classes, reclassify using clustering masks.
result Achieved state-of-the-art performance with an error rate of 11.56% on Cifar-100.
Unified view of contrastive and supervised learning improves model performance.
problem Improving model performance in classification, robustness, and detection.
method Hybrid discriminative-generative training of energy-based models.
result Improved performance on classification, robustness, out-of-distribution detection, and calibration.
Colored noise improves neural network robustness against adversarial attacks.
problem Vulnerability of neural networks to adversarial perturbations.
method Injection of colored noise into network weights and activations during adversarial training.
result Our approach outperforms previous methods in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets.
Graph Ricci flow reveals hidden hierarchies in stock market correlations.
problem Detecting hidden structures in the complex stock market graph.
method Using graph Ricci curvature and flow techniques to analyze the NASDAQ 100 index.
result Algorithm detects hidden hierarchies, community behavior, and clustering in financial markets.
Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is demonstrated to efficiently solve eigenvalue problems for graph Laplacians that appear in spectral clustering. For static graph partitioning, 10-20 iterations of LOBPCG without preconditioning result in ~10x error reduction, enough to achieve 100% corr…
Improved sample efficiency with normalized RBF kernels in neural networks.
problem Learning more with less data in deep learning models.
method Two-phase method to train neural networks with normalized RBF kernels as output layer.
result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.
Study improves risk management for volatile markets using expectiles.
problem Limitations of traditional risk measures during market stress.
method Develops expectile-based framework for FTSE 100 index.
result Expectile-based Value-at-Risk (EVaR) outperforms traditional VaR measures.
EENA efficiently searches neural architectures with minimal resources.
problem Lack of direction and high computational cost in neural architecture search.
method EENA uses guided evolution with mutation and crossover operations.
result EENA designs highly effective neural architectures with minimal resources.
CMTF improves financial market forecasting by fusing multiple data types.
problem Lack of effective integration of diverse financial data sources.
method Transformer-based deep learning framework with tensor interpretation and auto-training.
result CMTF outperforms classical and deep learning models in price direction classification.
MALT improves adversarial attacks by targeting classes more efficiently.
problem Naive targeting of adversarial attacks based on classifier confidence.
method MALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions.
result MALT wins over AutoAttack on CIFAR-100 and ImageNet datasets, five times faster.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
problem Adversarial examples often have different semantics than original data, introducing unintended biases.
method Semantics-preserving adversarial training (SPAT) that encourages pixel perturbation shared among all classes.
result SPAT improves adversarial robustness and achieves state-of-the-art results in CIFAR-10 and CIFAR-100.
This paper calibrates uncertainty in dropout variational inference models.
problem Uncertainty in variational inference with dropout is poorly calibrated.
method Temperature scaling is extended to dropout variational inference.
result Temperature scaling reduces miscalibration of uncertainty.
Proposes LML layer for multi-label predictions with k labels.
problem Efficient multi-label prediction with limited labels.
method Probabilistic multi-label modeling, efficient forward and backward passes.
result Improves top-k recall and accuracy in multi-label tasks.
New method enhances adversarial robustness of deep learning models.
problem Improving the robustness of deep learning models against adversarial attacks.
method Optimal transport regularized divergences applied to distributionally robust optimization.
result Improved adversarial robustness on CIFAR-10 and CIFAR-100 datasets.
A new mutual information optimization method using self-supervised binary contrastive learning.
problem Improving self-supervised contrastive learning for better model performance.
method Proposes a novel loss function for contrastive learning that optimizes mutual information in positive and negative pairs.
result The proposed method outperforms state-of-the-art self-supervised contrastive frameworks on various benchmark datasets.
BatchEnsemble reduces ensemble costs by 3X in training and testing.
problem High costs for training and testing ensembles of neural networks.
method Defines each weight matrix as a Hadamard product of a shared matrix and a rank-one matrix per member.
result Achieves 3X speedup and 3X memory reduction in test time for ensembles of size 4.
Improved clustering speed for 20 clusters on CIFAR-100 dataset.
problem Training time complexity for VAEs with discrete latent variables is linear in the number of clusters.
method Applied a continuous relaxation to discrete variables in Gaussian Mixture VAE, reducing training time complexity to constant.
result Reduced training time from 47 hours to 6 hours for 20 clusters on CIFAR-100.
A knot is called minimal if its knot group admits epimorphisms onto the knot groups of only the trivial knot and itself. In this paper, we determine which two-bridge knot b(p,q) is minimal where q≤6 or p≤100.
The paper addresses optimal control in modern tontines with bequest preferences, showing a linear investment strategy.
problem Optimal controls and decreasing allocation in modern tontines with bequest preferences.
method Dual approach to solve optimal control problems with power utilities, modeling bequest preferences.
result Investment strategy almost linearly adjusts from 0% to 100% over time.
New bound on neural network generalization error using geometric complexity.
problem Understanding the generalization capabilities of deep neural networks.
method Derive a new upper bound on generalization error using margin-normalized geometric complexity.
result Empirical validation of the bound for ResNet-18 on CIFAR-10 and CIFAR-100 datasets.
KD technique improves QDNN performance with reduced hyper-parameters.
problem Restoring performance loss in QDNNs due to quantization.
method Applied KD with reduced hyper-parameters, including a new coefficient reduction technique.
result Achieved 92.7% test accuracy on CIFAR-10 and 67.0% on CIFAR-100 with 2-bit weights.
This paper explores adversarial training limits and improves model robustness against norm-bounded perturbations.
problem Understanding and improving adversarial robustness of deep neural networks.
method Systematic study of adversarial training with various factors, including model size, activation functions, and unlabeled data.
result Training robust models that go beyond state-of-the-art results by combining larger models, Swish/SiLU activations, and model weight averaging.
Method detects and relabels noisy image labels to improve DNN performance.
problem Label noise in training images harms DNN generalization.
method Identifies noisy labels based on predictive uncertainty changes over training.
result Iterative relabeling of noisy labels improves DNN performance.
Reduces test set maintenance effort by 80-100%.
problem Lack of proper and up-to-date test sets in real-world scenarios.
method Simple technique to reduce labeling effort.
result Significant reduction in test set maintenance effort (80-100%).
High-dimensional partial differential equations (PDE) appear in a number of models from the financial industry, such as in derivative pricing models, credit valuation adjustment (CVA) models, or portfolio optimization models. The PDEs in such applications are high-dimensional as the dimension corresponds to the number …
Patch augmentation boosts neural network accuracy and robustness.
problem Improving neural network accuracy and robustness to adversarial attacks.
method Data augmentation technique creating new images by superimposing patches from image pairs.
result Significant accuracy improvements on CIFAR-10 and CIFAR-100 datasets.