StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
AugurOne trains single image generators without GANs using image warps.
problem Training end-to-end single image generators without GANs.
method Non-affine augmentations of single input images for training an upscaling neural network.
result End-to-end training yields state-of-the-art performance on conditional generation tasks.
New bounds show limitations of sample-wise information-theoretic generalization.
problem Limitations of sample-wise information-theoretic generalization bounds.
method Analysis of existing bounds and derivation of new bounds.
result No sample-wise information-theoretic bounds exist for expected squared generalization gap.
Single ReLU neuron's gradient dynamics reveal support vectors as key to generalization.
problem Understanding the generalization capability of ReLU networks.
method Examined gradient flow dynamics and support vectors in single ReLU neuron training.
result Support vectors play a crucial role in the generalization of ReLU networks.
Kernel methods estimate causal effects with a single proxy for deterministic confounders.
problem Estimating causal effects with a single proxy for an unobserved confounder.
method Two kernel-based methods: two-stage regression and maximum moment restriction.
result Both kernel methods can consistently estimate the causal effect.
New model generates realistic single-cell gene expression data.
problem Generating realistic single-cell gene expression profiles is challenging.
method scLDM, a latent diffusion model using Diffusion Transformers and linear interpolants.
result Superior performance in generating realistic single-cell gene expression data.
A method to generate multi-label data from single positive annotations.
problem Generating multi-label datasets is costly and impractical.
method Single-to-multi-label (S2M) sampling using Markov chain Monte Carlo.
result S2M sampling enables high-quality multi-label data with minimal annotation cost.
Paper proposes SiSTA for single-shot domain adaptation using target-aware generative augmentation.
problem Adapting models from source to target domains with limited target data.
method Fine-tunes a generative model on a single-shot target and uses novel sampling strategies for synthetic data.
result Improves performance by up to 20% over existing baselines in face attribute detection.
Overparameterized ensembles don't offer generalization benefits over single large models.
problem Theoretical limitations of ensembles in overparameterized settings.
method Using ensembles of random feature (RF) regressors, the paper clarifies how modern ensembles differ from underparameterized counterparts.
result Infinite ensembles of overparameterized RF regressors become pointwise equivalent to single infinite-width RF regressors, and finite width ensembles converge to single models with the same parameter budget.
New method separates and deconvolves signals from single-channel mixtures.
problem Separating and deconvolving individual sources from a single-channel mixture.
method Synthesizing-decomposition (S-D) approach using GAN for sources and optimization for filters and sources.
result Achieves PSNR improvements over existing methods in various tasks.
Single model detects abnormal samples across diverse tasks.
problem Detecting abnormal samples in machine learning.
method Introduced Diffusion Paths (DiffPath) using a single unconditional diffusion model.
result Single model performs OOD detection across diverse tasks.
Paper tackles continual learning with single-index models, proving regret bounds.
problem Continual learning with single-index models across multiple tasks.
method Proposes a randomized strategy to learn a common single-index and task-specific link functions.
result Proves regret bounds for the proposed strategy under various loss function assumptions.
It is investigated Hurwitz numbers, that correspond to covering of disk with single non-simple boundary critical value. It is found differential equations, that describe a generating function for these numbers.
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of networks which generalize and those which do not remain unclear. Additionally, the tuning properties of single directions (defined as the activa…
Model reconstructs novel 3D shapes with a single prior image.
problem Generalizing single-view 3D reconstruction to new classes with limited data.
method Reframes reconstruction as refinement of a provided prior shape.
result Model reconstructs novel classes with limited training data.
New algorithm reduces regret for single-index bandits to nearly optimal.
problem Optimizing rewards from unknown projections of high-dimensional contexts.
method Two-phase algorithm: estimate projection direction, reduce to 1D bandit, use UCB.
result Achieved optimal regret of ildeO(T2/3). Improved regret for single-index bandits with optimal algorithm.
problem Optimizing rewards from unknown one-dimensional projections of high-dimensional contexts.
method Two-phase algorithm: first estimate projection direction, then discretize and use UCB.
result Achieved optimal regret of ildeO(T2/3). Single-stage neural architecture improves text-to-image synthesis.
problem Combining text and image generation is challenging.
method Used deep residual networks and sentence interpolation.
result Achieved state-of-the-art performance with single-stage training.
New algorithm accelerates single-pass SGD for generalized linear prediction.
problem Improving single-pass non-quadratic stochastic optimization.
method Data-dependent proximal method incorporating dual-momentum acceleration.
result Momentum acceleration resolves open problem in streaming setting.
Study SGD dynamics in sequence models, revealing training phases and influence of sequence length.
problem Understanding SGD in sequence models like attention networks.
method Derived closed-form population loss and analyzed SGD dynamics for SSI models.
result Two distinct training phases: escape from uninformative initialization and alignment with target subspace.
New neural networks learn single-index models efficiently.
problem Learning low-dimensional structure in high-dimensional data.
method Shallow neural networks with frozen biases, studied via gradient flow.
result Generalization guarantees match near-optimal sample complexity.
The paper explores a Multi-Objective RL approach for trading that generalizes reward functions.
problem Improving performance in single-asset trading through adaptive reward functions.
method Developed a Multi-Objective Deep Reinforcement Learning algorithm to generalize reward functions and discount factors.
result The Multi-Objective algorithm demonstrates increased predictive stability and better performance in sparse reward scenarios.
SGD shows distinct phases in learning single-index models, achieving optimal sample complexity and regret.
problem Learning single-index models with SGD in adaptive data settings.
method Stochastic gradient descent (SGD) with an optimal learning rate schedule.
result SGD achieves near-optimal sample complexity and regret guarantees across both burn-in and learning phases.
sgdGMF efficiently estimates generalized matrix factorization models for single-cell RNA sequencing data.
problem Challenges in dimensionality reduction for large single-cell RNA sequencing datasets.
method Scalable adaptive stochastic gradient descent algorithm for generalized matrix factorization models.
result sgdGMF outperforms existing methods in scalability and accuracy for large datasets.
MarkerMap selects key genes for cell type analysis in single-cell RNA-seq.
problem Selecting informative genes from large single-cell RNA-seq datasets is challenging and computationally intensive.
method MarkerMap is a generative model that identifies minimal gene sets explaining cell type variability.
result MarkerMap outperforms existing methods in both supervised and unsupervised marker selection.
Unified CLIP space manipulations improve GAN adaptation with a single target image.
problem Overfitting or underfitting in fine-tuning a pre-trained generator with a single target image.
method Two-step training strategy: latent optimization in CLIP space followed by generator fine-tuning with CLIP space consistency loss.
result Our model generates diverse outputs with the target texture and outperforms baseline models.
A new pyramidal diffusion model speeds up image generation.
problem Training and evaluating diffusion models are time-consuming.
method Introduces a pyramidal diffusion model with a single score function.
result Generates high-resolution images from low-resolution starting points efficiently.
Approach generates multiple correct predictions from single supervision.
problem Single correct prediction from multiple possible alternatives.
method Develops an approach to generate multiple high-quality predictions.
result Can generate high-quality outputs different from observed.
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Develops a new method for efficient stochastic bilevel optimization.
problem Stochastic bilevel optimization problems in machine learning applications.
method Single-Timescale stochAstic BiLevEl optimization (STABLE) method.
result Achieves the same order of sample complexity as stochastic gradient descent for single-level optimization.
A new method reduces adversarial training time without overfitting.
problem Catastrophic overfitting in single-step adversarial training.
method FGSMPR: FGSM with PGD Regularization.
result Reduces the gap to multi-step adversarial training.
New method uses surrogate outcomes and single-record data to improve suicide risk modeling.
problem Lack of historical information in single-record patients hinders modeling rare medical events.
method Hybrid framework combining supervised and unsupervised learning to integrate concurrent and single-record data.
result Single-record data and concurrent diagnoses provide valuable information for improving suicide risk modeling.
Single episode policy transfer in RL without access to rewards.
problem Performing near-optimally in a single attempt with unknown dynamics.
method Optimizes a probe and inference model to estimate latent variables for universal control policy.
result Significantly outperforms existing adaptive approaches in diverse domains.
GANPOP uses deep learning to estimate optical properties from single images, improving accuracy over existing methods.
problem Estimating optical properties from single wide-field images.
method Conditional generative adversarial networks trained on paired images and optical property maps.
result GANPOP estimates optical properties with 58% higher accuracy than single-snapshot optical property technique in human gastrointestinal specimens.
Single Class Universum-SVM uses additional data to improve single class learning.
problem Improving single class learning with limited positive data.
method Proposes Single Class Universum-SVM, incorporating additional data with different distribution.
result Empirical comparisons show the utility of the proposed approach.
TOAD-GAN generates coherent game levels from a single example.
problem Creating game levels from a single example.
method Token-based Procedural Content Generation (PCG) using SinGAN architecture.
result Achieves state-of-the-art results in generating coherent levels of similar style.
Single model learns physics from diverse data.
problem Lack of universal physics models for diverse applications.
method General Physics Transformer (GPhyT) trained on diverse physics data.
result Single model achieves superior performance across multiple physics domains.
We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-conditionals or the joint distribution, and does not require a priori knowledge of the number of classes or the relationships between classes. Th…
Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of …
Gradient methods learn a single neuron under mild assumptions.
problem Learning a single neuron with gradient methods under realistic conditions.
method Gradient methods applied to a single neuron model.
result Positive guarantees achieved under mild assumptions, beyond previous literature.
Proposes CCCVAE for better single-cell clustering with cell-cell communication.
problem Improving single-cell RNA sequencing clustering by incorporating cell-cell communication.
method Integrates cell-cell communication into a variational autoencoder framework.
result Empirical results show CCCVAE outperforms standard VAEs in clustering performance.
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
New bounds on learning algorithm generalization error derived using information density.
problem Bounding the generalization error of learning algorithms.
method Exponential inequalities and information density/conditional information density.
result Novel bounds on average and tail probability of generalization error.
Rugby-Bot predicts multiple metrics from a single source using fine-grain data.
problem Complexity of sporting events requires multiple metrics for accurate analysis.
method Multi-task learning with fine-grain spatial data and wide-and-deep learning.
result Predictions are consistent and can be in distribution form.
ChemCPA predicts cellular responses to novel drugs using transfer learning.
problem Scaling high-throughput screens to measure cellular responses for many drugs is costly and challenging.
method ChemCPA, a new encoder-decoder architecture combined with transfer learning.
result Training on existing bulk RNA HTS datasets improves generalization performance, reducing the need for extensive single-cell screens.
Let M be a hyperkähler manifold. The S^2-family of complex structures compatible with the hyperkähler metric can be assembled into a single complex structure on Z=MxS^2; the resulting complex manifold is known as the twistor space of M. We describe the analogous construction for generalized complex structures in the se…
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
problem Synthesizing novel views from a single image with large viewpoint changes.
method Shrink-wrapping a planar mesh sheet onto the input image, consistent with learned depth.
result Worldsheet consistently outperforms prior methods on single-image view synthesis.
Algorithm learns weight matrix from single trajectory of nonlinear dynamical system.
problem Learning weight matrix from a single trajectory of nonlinear dynamical system.
method Algorithm uses global stability and well-conditioned covariance to recover weight matrix.
result Algorithm recovers weight matrix with optimal sample complexity and linear running time.