arXiv research

New model improves diversity in question generation over text.

Improves generative Visual Dialog by asking diverse questions.

Diversity or complementarity of experts in ensemble pattern recognition and information processing systems is widely-observed by researchers to be crucial for achieving performance improvement upon fusion. Understanding this link between ensemble diversity and fusion performance is thus an important research question. …

We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual conce…

Research finds investors may lose from more diverse workplaces.

As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks? To approach this question, deep multi-task learning is extended in this paper to the setting where there is no obvious overlap between task a…

Quriosity analyzes curiosity-driven questions from diverse sources.

Generating molecules with desired chemical properties is important for drug discovery. The use of generative neural networks is promising for this task. However, from visual inspection, it often appears that generated samples lack diversity. In this paper, we quantify this internal chemical diversity, and we raise the …

Paper tackles diversity in Airbnb search results.

A financial market is called "diverse" if no single stock is ever allowed to dominate the entire market in terms of relative capitalization. In the context of the standard Ito-process model initiated by Samuelson (1965) we formulate this property (and the allied, successively weaker notions of "weak diversity" and "asy…

Study finds optimal board gender diversity for emissions performance.

The study provides precise asymptotic theory for in-context learning by Transformers.

We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality, relevance or diversity in the answer options. Our method addresses these problems by leveraging a large corpus of domain-speci…

When constructing a classifier ensemble, diversity among the base classifiers is one of the important characteristics. Several studies have been made in the context of standard static data, in particular, when analyzing the relationship between a high ensemble predictive performance and the diversity of its components.…

Condorcet's Jury Theorem has been invoked for ensemble classifiers to indicate that the combination of many classifiers can have better predictive performance than a single classifier. Such a theoretical underpinning is unknown for consensus clustering. This article extends Condorcet's Jury Theorem to the mean partitio…

DASH improves ensemble generalizability by encouraging diverse, flat loss landscapes.

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to…

Underrepresented scientists produce more novel work but it's undervalued.

New hyperbolic manifolds with diverse features created.

Meta Omnium benchmarks few-shot learning across diverse vision tasks.

INNs can approximate diverse functions despite layer restrictions.

VTAB benchmarks diverse visual tasks to assess representation learning effectiveness.

This paper proposes a new method to connect language and physical actions in reinforcement learning.

End-to-End training (E2E) is becoming more and more popular to train complex Deep Network architectures. An interesting question is whether this trend will continue-are there any clear failure cases for E2E training? We study this question in depth, for the specific case of E2E training an ensemble of networks. Our str…

A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the distributions they are trained on. In particular, evaluating the diversity of GAN distributions is challenging and existing method…

Unified framework improves NLP tasks by converting diverse problems into text-to-text format.

Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context…

A new learning rule consistently reduces error over data samples.

SKADA-bench evaluates unsupervised DA methods across diverse modalities.

Identifies latent actions and dynamics from offline data with diverse demonstrators.

FinanceBench benchmarks LLMs on financial QA, revealing limitations.

Large Question-and-Answer (Q&A) platforms support diverse knowledge curation on the Web. While researchers have studied user behavior on the platforms in a variety of contexts, there is relatively little insight into important by-products of user behavior that also encode knowledge. Here, we analyze and model the macro…

Paper tackles sample-efficient offline RL, proposing data diversity and unified algorithms.

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of…

EasyTime simplifies time series forecasting for researchers and practitioners.

The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can express a variety of widely used models from unsupervised learning. To enable mod…

For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could hurt the learning process. This paper questions this common percep…

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…

Survey on metric SYZ conjecture and non-archimedean geometry.

Study evaluates reinforcement learning for trading diverse stocks, finds Q-learning outperforms.

New theory improves understanding of ensemble learning systems.

Stacked models improve link prediction across diverse networks.

Jigsaw-VAE tackles feature imbalance in VAE latent variables, improving generalization across environments.

Unified approach for multimodal data prediction using synthetic data generation.

HEAR benchmark evaluates audio representations for diverse tasks.

In contrast to an infinite family of explicit examples of two-dimensional $p$-harmonic functions obtained by G.Aronsson in the late 80s, there is very little known about the higher-dimensional case. In this paper, we show how to use isoparametric polynomials to produce diverse examples of $p$-harmonic and biharmonic fu…

The paper proposes a method to verify tree ensembles by reasoning about potential instances.

New method estimates robust multi-period portfolios using entropy.