A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
D-CBRS manages memory for continual learning by accounting for intra-class diversity.
This work studies the impact of intra-/inter-class diversity on pre-training datasets and finds a balance for optimal performance.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
New analysis shows diverse classes in pre-training boost NLP performance.
Neural Laplace models diverse DEs in the Laplace domain for better dynamics.
High-dimensional diffusion models suffer from distorted samples due to CFG.
The study identifies latent concepts from diverse observations without assuming specific models.
Training task diversity improves ICL with linear attention.
Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 r…
Strongly log-concave (SLC) distributions are a rich class of discrete probability distributions over subsets of some ground set. They are strictly more general than strongly Rayleigh (SR) distributions such as the well-known determinantal point process. While SR distributions offer elegant models of diversity, they lac…
New statistical guarantees for transfer learning with diverse tasks.
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations shoul…
Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by…
Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occurrence of bias (under- or over-representation of a certain gender or race) in such data summarization methods. In this paper we initiate a s…
We describe society as a nonequilibrium probabilistic system: N individuals occupy W resource states in it and produce entropy S over definite time periods. Resulting thermodynamics is however unusual because a second entropy, H, measures a typically social feature, inequality or diversity in the distribution of availa…
New hyperbolic manifolds with diverse features created.
Meta-learning performance improved by keeping support sets fixed.
We analyze different re-ranking algorithms for diversification and show that majority of them are based on maximizing submodular/modular functions from the class of parameterized concave/linear over modular functions. We study the optimality of such algorithms in terms of the `total curvature'. We also show that by adj…
Study evaluates three class imbalance techniques across diverse datasets.
Paper tackles sample-efficient offline RL, proposing data diversity and unified algorithms.
Paper tests DPPs for diversity models, distinguishing them from other distributions.
DAMVI algorithm improves imbalanced binary classification by adjusting weights of examples and classifiers.
Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution…
While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work of Arora et al. suggests a dilemma about GANs' statistical properties: powerful d…
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploratio…
Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a better fit to the target data distribution when the dataset includes many different…
LIMEtree offers faithful explanations for multiple classes in predictive models.
New findings on representation learning beyond linear functions.
SteinGen generates diverse graph samples from a single example.
New method prevents class collapse in metric learning with margin-based losses.
Established equivalence of Atiyah classes for generalized holomorphic vector bundles.
URT layer improves few-shot image classification across diverse domains.
It is widely known in the machine learning community that class noise can be (and often is) detrimental to inducing a model of the data. Many current approaches use a single, often biased, measurement to determine if an instance is noisy. A biased measure may work well on certain data sets, but it can also be less effe…
Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respe…
We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different gener…
Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels. The meta-learning approaches train a meta learner to predict weight…
New algorithms for model selection in linear contextual bandits without feature diversity conditions.
We identify and study a class of hyperbolic 3-manifolds (which we call Macfarlane manifolds) whose quaternion algebras admit a geometric interpretation analogous to Hamilton's classical model for Euclidean rotations. We characterize these manifolds arithmetically, and show that infinitely many commensurability classes …
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities. Specifically, BigGANs a class-conditional Generative Adversarial Networks trained on ImageNet---achieved excellent, state-of-the-art capability in generating realistic photos. However, fine-tuning …
New method designs joint initial noises for diffusion models to improve diversity and alignment.
Flexible evidential deep learning improves uncertainty quantification in machine learning.
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications. This paper proposes an error-correcting neural network (ECNN) that combines a set of binary classifiers to combat adversarial examples in the multi-c…
BOP-Elites uses Bayesian Optimisation for QD search, improving efficiency and insight.
This work introduces an efficient method to sample high-quality images from conditional GANs.
Ensembles, as a widely used and effective technique in the machine learning community, succeed within a key element -- "diversity." The relationship between diversity and generalization, unfortunately, is not entirely understood and remains an open research issue. To reveal the effect of diversity on the generalization…
Unified kernels for diverse applications in math and stats.
Framework for handling long-tailed multi-modal data.
Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models. We propose D-City, a large-scale comprehensive collection of dash…