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.
Paper explores how text generation quality and diversity metrics relate to distribution fitting.
New model improves diversity in question generation over text.
New measures quantify diversity of latent representations using metric space magnitude.
Study shows diverse data sources improve cryptocurrency forecasting models.
The paper improves experimental design by weighting diversity metrics with quality, leading to more diverse and effective discoveries.
Proposes Vendi Score for evaluating diversity in ML models.
New metric evaluates generative models across domains, diagnosing fidelity, diversity, and generalization.
This research introduces a new strategy in cluster ensemble selection by using Independency and Diversity metrics. In recent years, Diversity and Quality, which are two metrics in evaluation procedure, have been used for selecting basic clustering results in the cluster ensemble selection. Although quality can improve …
Heterogeneous SVO leads to diverse policies in sequential social dilemmas.
Text generation is an important Natural Language Processing task with various applications. Although several metrics have already been introduced to evaluate the text generation methods, each of them has its own shortcomings. The most widely used metrics such as BLEU only consider the quality of generated sentences and…
Ensembles depend on diversity for improved performance. Many ensemble training methods, therefore, attempt to optimize for diversity, which they almost always define in terms of differences in training set predictions. In this paper, however, we demonstrate the diversity of predictions on the training set does not nece…
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
Thanks to the recent availability of comprehensive and detailed online databases of startup companies, it has become possible to more directly investigate startup ecosystems i.e. startup populations in specific regions. In this paper, we analyze the emergence of 20+ such ecosystems in Europe and the USA, with a specifi…
MO-PaDGAN generates diverse, high-performance designs with multiple metrics.
New metrics improve reliability of image generation evaluation.
METASET selects diverse unit cells for efficient data-driven metamaterial design.
How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set. On the other hand, statistical evaluation (i.e., perplexity) captures diversity b…
The need for diversification of recommendation lists manifests in a number of recommender systems use cases. However, an increase in diversity may undermine the utility of the recommendations, as relevant items in the list may be replaced by more diverse ones. In this work we propose a novel method for maximizing the u…
Novel method decorrelates batches of triplets for active metric learning.
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…
Product diversity of large US firms has declined steadily since 1997.
Study flaws in generative model evaluation metrics, especially for diffusion models.
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…
Proposes a method to generate diverse translations by conditioning on target domain.
AlphaEval evaluates alpha mining models efficiently and comprehensively.
Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from ob…
Clustering explores meaningful patterns in the non-labeled data sets. Cluster Ensemble Selection (CES) is a new approach, which can combine individual clustering results for increasing the performance of the final results. Although CES can achieve better final results in comparison with individual clustering algorithms…
Two proteins are homologous if they have a common evolutionary origin, and the binary classification problem is to identify proteins in a candidate set that are homologous to a particular native protein. The feature (explanatory) variables available for classification are various measures of similarity of proteins. The…
Enhances multimodal generation with Normalizing Flows and correlation analysis.
Real-world machine learning applications often have complex test metrics, and may have training and test data that are not identically distributed. Motivated by known connections between complex test metrics and cost-weighted learning, we propose addressing these issues by using a weighted loss function with a standard…
PGEL learns embeddings to diversify protein motifs while maintaining biological function.
Causal analysis predicts market trends using time series data.
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. However, the diversity in appl…
This paper introduces new invariants for time series analysis.
We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression. AIQN is able to achieve superior perceptual quality and improvements in evaluation metrics, without incu…
New method prevents class collapse in metric learning with margin-based losses.
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…
Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such as mobile and other consumer devices given their high computational and memory …
Survey on metric SYZ conjecture and non-archimedean geometry.
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
RNE tackles scalable recommendation for billion-scale scenarios.
Paper proposes SDRL to improve continual learning with less computational cost.
New method designs joint initial noises for diffusion models to improve diversity and alignment.
The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, assessing the performance of such generative models is notoriously difficult. Metrics that are typically used to assess the performance of such generative models are the perc…
Improves diversity of text-to-image models without sacrificing FID.
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforceme…
Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge …
PerturBench benchmarks ML models for cellular perturbation analysis.