Study shows how to manipulate VAEs for attacks and assess their robustness.
problem Adversarial attacks on Variational Autoencoders (VAE).
method Examine modifications to VAEs and propose metrics for robustness.
result Metrics to quantify the robustness of VAEs to adversarial attacks.
Horovod simplifies multi-GPU training in TensorFlow.
problem Efficient multi-GPU training in TensorFlow with minimal code changes.
method Efficient inter-GPU communication via ring reduction and minimal code modifications.
result Faster, easier distributed training in TensorFlow.
Study makes code models robust to small changes that keep functionality.
problem Vulnerability of deep neural networks to adversarial examples in source code.
method Defined a powerful adversary and adversarial training to learn robust models.
result Significant gains in robustness demonstrated across different languages and architectures.
Improved β-VAE learns disentangled representations without sacrificing reconstruction accuracy.
problem Learning disentangled representations in variational autoencoders (VAEs).
method Modified β-VAE training regime that increases latent code information capacity over training. result Improved β-VAE robustly learns disentangled representations without sacrificing reconstruction accuracy. Developed HIquant to quantify proteoforms accurately without biases.
problem Peptide-specific biases in quantifying proteoforms by MS methods.
method First-principles model (HIquant) for quantifying proteoform stoichiometries.
result High accuracy in quantifying fractional PTM occupancy without external standards.
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.
Improved stability in DQN using neural networks with modifications.
problem Stability issues in DQN with neural networks.
method Simple modifications to neural network structure.
result Improved stability in DQN learning.
ABIForest improves anomaly detection using attention weights.
problem Anomaly detection in datasets.
method Attention mechanism integrated into Isolation Forest.
result ABIForest outperforms standard Isolation Forest on synthetic and real datasets.
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.
Deep learning optimizes constellation for two-way relaying networks, boosting sum rate.
problem Optimizing constellation for better performance in two-way relaying networks.
method Deep neural networks (DNNs) trained to minimize cross entropy loss for direct constellation optimization.
result Significant performance gain in achievable sum rate compared to conventional relaying schemes.
BayesDLL offers a PyTorch library for Bayesian deep learning with large models.
problem Bayesian inference for large-scale deep networks.
method Variational inference, MC-dropout, stochastic-gradient MCMC, Laplace approximation.
result BayesDLL can handle Vision Transformers and pre-trained model weights as priors.
Method generates adversarial examples to improve classifier robustness.
problem Addressing adversarial examples in machine learning.
method MDL principle for generating adversarial examples.
result Evasion rate of 78.24% for adversarial examples compared to 8.16% for original malware.
DGPs enhanced with GVI improve robustness and uncertainty quantification.
problem Improving robustness and uncertainty quantification in deep Gaussian processes.
method Integrating Generalized Variational Inference (GVI) into Deep Gaussian Processes (DGPs).
result DGPs show significant benefits from GVI modifications in empirical tests.
A simple modification improves GAN performance by discarding bad samples.
problem Improving GAN performance with minimal computational cost.
method Top-k update procedure: zero out gradient contributions from least realistic elements.
result Significant improvement in FID score for conditional generation on CIFAR-10.
DP-REC combines privacy and communication efficiency in federated learning.
problem Combining privacy and communication efficiency in federated learning.
method DP-REC uses Relative Entropy Coding (REC) for compression and a minor modification for differential privacy.
result DP-REC reduces communication costs while maintaining privacy comparable to state-of-the-art methods.
Paper refines InfoNCE for accurate mutual information estimation.
problem Indirect connection of InfoNCE to mutual information estimation.
method Introduces InfoNCE-anchor with an auxiliary anchor class for consistent density ratio estimation.
result InfoNCE-anchor yields a plug-in MI estimator with significantly reduced bias.
Generative AI tasks analyzed for text, images, audio, video, code, and molecules.
problem What is the core question when using generative AI?
method Survey of generative model families, probabilistic framework, game-theoretic setup, post-training modifications, socially responsible considerations.
result Generative AI is a distinct machine learning task with connections to prediction, compression, and decision-making.
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.
HECT tests climate model outputs for reproducibility.
problem Ensuring climate models accurately reflect physical processes.
method Probabilistic classifiers for high-dimensional spatio-temporal data.
result A principled way to assess statistical reproducibility of climate models.
Ensembles of classification and regression trees remain popular machine learning methods because they define flexible non-parametric models that predict well and are computationally efficient both during training and testing. During induction of decision trees one aims to find predicates that are maximally informative …
ULMFiT improves NLP tasks with transfer learning.
problem Task-specific modifications and training from scratch in NLP.
method Universal Language Model Fine-tuning (ULMFiT) with transfer learning.
result Significantly outperforms state-of-the-art on six text classification tasks.
GradPower speeds up language model training with minimal code changes.
problem Slower training of large language models.
method Elementwise sign-power transformation applied to gradients.
result Consistently lower terminal loss across various models and datasets.
Proposes methods to improve hierarchical classification accuracy by flattening inconsistent nodes.
problem Error propagation in top-down hierarchical classification due to inconsistent nodes.
method Data-driven approaches for identifying and flattening inconsistent nodes.
result Improves classification performance by up to 7% in Macro-F1 score.
Improved diffusion models solve inverse problems more accurately by correcting sample paths off the data manifold.
problem Current diffusion models for inverse problems often produce suboptimal results due to sample paths deviating from the data manifold.
method Proposed an additional correction term inspired by manifold constraints to make iterations closer to the data manifold.
result The proposed method boosts performance by a large margin, producing promising results in various applications.
RotationOut rotates input vectors to regularize neural networks.
problem Reduction of co-adaptation in neural networks.
method Randomly rotates input vectors of the input layer.
result RotationOut reduces co-adaptation better than Dropout.
RPO uses past and future state-action info for better policy optimization.
problem Sample inefficiency in on-policy reinforcement learning methods.
method Reflective Policy Optimization (RPO) integrates past and future state-action info for policy improvement.
result RPO improves policy performance and contracts the solution space, leading to faster convergence.
New method detects RNA modifications without prior training, revealing novel sites.
problem Detecting RNA modifications with high accuracy and sensitivity.
method Anomaly detection using nanopore raw ionic current signals and nearest neighbor comparison.
result Detects diverse RNA modifications without prior training, including a novel 2'-O-methylated site in DENV.
We define an operation on homology B4 which we call an n-twist annulus modification. We give a new construction of smoothly slice knots and exotically slice knots via n-twist annulus modifications. As an application, we present a new example of a smoothly slice knot with non-slice derivatives. Such examples we…
IDF++ improves integer discrete flows for lossless compression.
problem Theoretical limitations of integer discrete flows for lossless compression.
method Investigated and improved integer discrete flows, addressing gradient bias and architecture modifications.
result Different architecture modifications improve integer discrete flows for lossless compression.
Study shows stability of locally conformally balanced condition under modifications but not under small deformations.
problem Stability of locally conformally balanced condition under small deformations and modifications.
method Proved stability under proper modifications and instability under small deformations using examples and Hilbert-Chow map.
result Stability of locally conformally balanced condition under proper modifications and instability under small deformations.
Improves GANs by incorporating class information with a multi-hinge loss.
problem Improving GANs to better respect class information.
method Proposes a multi-class generalization of the Hinge loss for GANs.
result Improves Inception Scores and Frechet Inception Distance on Imagenet.
Proposes simplified SHAP for faster black-box model explanations.
problem Computational expense of SHAP for models with many features.
method Ensemble of random SHAPs with feature selection and point generation.
result Efficiency and properties demonstrated through numerical experiments.
Behavior modification improves prediction accuracy by nudging user behavior.
problem Improving prediction accuracy using behavior modification techniques.
method Combining prediction and behavior modification with reinforcement learning algorithms.
result Behavior modification can make predictions more certain but may not generalize.
Improved DDPMs achieve high log-likelihoods and sample quality with fewer passes.
problem Improving log-likelihoods of DDPMs while maintaining high sample quality.
method Modifying DDPMs with learning variances and using precision-recall metrics.
result DDPMs can achieve competitive log-likelihoods with fewer forward passes.
Paper proposes adversarial modifications for link prediction models to improve robustness and interpretability.
problem Improving accuracy is not enough; robustness and interpretability are also crucial for link prediction models.
method Adversarial modifications to identify influential facts and evaluate model sensitivity and interpretability.
result The approach identifies the most influential facts and evaluates the sensitivity of link prediction models to additional facts.
Study of unimodular Sasaki and Vaisman Lie groups, determining all modifications explicitly.
problem Classifying unimodular Sasaki and Vaisman Lie groups.
method Applying the technique of modification to determine all homogeneous Sasaki and Vaisman manifolds of unimodular Lie groups explicitly.
result Complete classification of unimodular Sasaki and Vaisman Lie groups.
We study large-scale classification problems in changing environments where a small part of the dataset is modified, and the effect of the data modification must be quickly incorporated into the classifier. When the entire dataset is large, even if the amount of the data modification is fairly small, the computational …
Adaptive weighting improves Deep Forest classifier's performance.
problem Improving Deep Forest classifier's efficiency and accuracy.
method Adaptive weighing of training instances at each cascade level, inspired by AdaBoost.
result The modified Deep Forest classifier performs better than the original.
Evolutionary algorithm finds optimal pixel perturbations to improve neural network generalization.
problem Minimal data corruption by pixel modifications causes overfitting in neural networks.
method Evolutionary algorithm with a novel cost function to maximize generalization gap and domain divergence.
result Method outperforms previous pixel-based data distribution shift methods on CNNs.
TyXe enables flexible Bayesian neural networks in Pytorch.
problem Uncertainty estimation in neural networks.
method Separates architecture, prior, inference, and likelihood specification; modular choices for priors, guides, and inference techniques.
result Minimal modifications to existing code for Bayesian neural networks.
Method explains anomaly detection by generating normal modifications.
problem Complexity of deep learning methods in anomaly detection.
method Generates multiple alternative modifications for anomalies.
result High-quality semantic explanations provided for anomaly detection.
We study Khovanov homology classes which have state cycle representatives, and examine how they interact with Jacobsson homomorphisms and Lee's map Φ. As an application, we describe a general procedure, quasipositive modification, for constructing H-thick knots in rational Khovanov homology. Moreover, we show that sp…
Preserves hyperbolicity in link complements with two moves.
problem Maintaining hyperbolicity in link complements.
method Chain move and switch move to preserve hyperbolicity.
result Preserves hyperbolicity in a substantial number of links.
The perceptron's compression is explored and applied to neural networks.
problem Understanding and improving the perceptron's margin and compression.
method Modifications to the perceptron algorithm and deductions from compression.
result Better guarantees on the margin of the perceptron's hyperplane.
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
problem Testing conditional independence
method Testing-by-betting on an adaptively optimized Kernel Conditional Independence statistic
result Significantly reduces Type I error inflation while preserving high power
iREPA shows spatial structure, not global semantic, drives generation performance in REPA.
problem Understanding what aspect of the target representation matters for generation.
method Empirical analysis of 27 vision encoders, two modifications to REPA.
result Spatial structure, not global semantic, drives generation performance.
Paper proposes using pairwise feature comparisons to infer modification costs for user recourse.
problem Learning and inferring user preferences for modifying features in black-box models.
method Bradley-Terry model for inferring feature-wise costs from non-exhaustive human comparison surveys.
result Non-exhaustive human surveys can efficiently learn feature costs, enabling recourse finding.
Max-Cut decision tree improves classification accuracy and reduces computation time.
problem Improving decision tree accuracy and efficiency for complex classification tasks.
method Alternative splitting metric (max cut) and PCA-based feature selection at each node.
result 49% improvement in accuracy with 94% reduction in CPU time on CIFAR-100 data.