arXiv research

Diffusion models struggle in high dimensions due to objective function degradation.

New framework for resilient bi-criteria optimization under noisy feedback.

Study optimizes HTL-free PSCs with MWCNTs, improving efficiency and stability.

Develops a new method to improve performance in multi-objective learning problems.

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

RLVR maintains safety while improving reasoning capabilities in LLMs.

Theoretical study explains why federated optimization fails to achieve perfect fitting.

The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets,…

New sparsity attacks degrade DNN efficiency, raising concerns for resource-constrained systems.

This paper optimizes power grid protection settings to maximize network degradation due to cascading attacks.

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

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

This work overcomes bias in concave multi-objective reinforcement learning.

New model tackles real-world distribution mismatches in machine learning.

New algorithm improves multitask learning across diverse agents.

A new method for fair classification using characteristic function distance.

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability…

This research improves multimodal systems by adding a second objective and regularisation methods.

AdaScale SGD adapts learning rates for large-batch training efficiently.

A new method to protect enterprise data privacy in AI models.

Soft geometric bias improves physical dynamics predictions.

Despite the recent successes of deep neural networks, the corresponding training problem remains highly non-convex and difficult to optimize. Classes of models have been proposed that introduce greater structure to the objective function at the cost of lifting the dimension of the problem. However, these lifted methods…

New method stabilizes private LASSO for high-dimensional data with diverse covariate scales.

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized inference distributions and, in some cases, improving the objective provably degra…

Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.

Measures DNA quality degradation effects.

Modeling coating degradation with fewer data points.

The most common method for DNN pruning is hard thresholding of network weights, followed by retraining to recover any lost accuracy. Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy deg…

Paper uses deep learning to model systems with degrading behavior.

Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.

Statistical test detects model degradations in optimized language models.

Novel method decorrelates batches of triplets for active metric learning.

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

Paper improves privacy-preserving measurement of advertising incrementality.

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal splitting method for the iterative solution of hierarchical sparse coding problem…

We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find the human visual system to be more robust to nearly all of the tested image manip…

New BO method optimizes functions efficiently even with unknown hyperparameters.

BAxUS optimizes high-dimensional functions adaptively, avoiding performance degradation and failure.

Ensemble pruning, selecting a subset of individual learners from an original ensemble, alleviates the deficiencies of ensemble learning on the cost of time and space. Accuracy and diversity serve as two crucial factors while they usually conflict with each other. To balance both of them, we formalize the ensemble pruni…

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

Deep RL for portfolio management shows poor robustness.

Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…

Self-supervised method enhances ultrasound images without needing clean targets.

Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algo…

Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade the quality of target output which hinders adoption of deep learning on an edge d…

Paper uses neural networks to predict NOx emissions from gas turbines.

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical evidence indicating that networks corresponding to lower-lying minima in the opt…

A geometric theory explains loss functions for robust representation learning.