arXiv research

New measure quantifies task difficulty for machine learning models.

Some statistical models are specified via a data generating process for which the likelihood function cannot be computed in closed form. Standard likelihood-based inference is then not feasible but the model parameters can be inferred by finding the values which yield simulated data that resemble the observed data. Thi…

Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where t…

Despite the significant advances in recent years, Generative Adversarial Networks (GANs) are still notoriously hard to train. In this paper, we propose three novel curriculum learning strategies for training GANs. All strategies are first based on ranking the training images by their difficulty scores, which are estima…

Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more sophisticated models and the incorporation of different expressive modalities (…

Proposes a simple framework to balance task difficulty in multi-task learning.

Reasoning models generate differently based on problem difficulty, not just length.

Deep networks prioritize easier examples over harder ones, leading to faster training.

Measures difficulty of predictions to improve deep learning models.

Improved PAC-Bayesian bounds by considering example difficulty.

The difficulty of classification affects the weight matrices' heavy tail appearance in deep learning networks.

We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then t…

New ensemble models classify mouse movement trajectories to assess survey question difficulty.

Research uses CPS to estimate uncertainty in ML radio metric models.

The paper uses geometry to assess how hard examples are for NLP models.

These notions in the title are of fundamental importance in any branch of physics. However, there have been great difficulties in finding physically acceptable definitions of them in general relativity since Einstein's time. I shall explain these difficulties and progresses that have been made. In particular, I shall i…

We present an algorithm to generate synthetic datasets of tunable difficulty on classification of Morse code symbols for supervised machine learning problems, in particular, neural networks. The datasets are spatially one-dimensional and have a small number of input features, leading to high density of input informatio…

Mathematical Reinforcement Learning faces a 'Two-Hump' problem due to sparse rewards and a scarcity of intermediate 'hard-but-solvable' instances.

Researchers calculated EVaR for various distributions using Lambert function.

Salzmann's legacy in mathematics documented.

The control of the costs, as soon as possible of the product life cycle, became a major asset in the competitiveness of the companies confronted with the universalization of competition. After having proposed the problems related this control difficulties, we will present an approach defining a concept of cost entity r…

Paper shows training can improve GCN performance without changing architecture.

Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which …

This study introduces balanced DRPS and OrderedLogitNN for better QDE of discrete-level questions.

This paper offers a mathematical introduction to GANs.

Learning shrinks hard tail, improving inference performance.

New method for Bayesian neural networks reduces inference difficulty.

In the early phases of the product life cycle, the costs controls became a major decision tool in the competitiveness of the companies due to the world competition. After defining the problems related to this control difficulties, we will present an approach using a concept of cost entity related to the design and real…

The paper explores when to prioritize easy or hard samples in learning tasks.

We study the relation between an R-Cartan structure α and an (I, J, K)- generalized Finsler structure on a 3-manifold showing the difficulty in finding a general transformation that maps these structures each other. In some particular cases, the mapping can be uniquely determined by geometrical conditions.

SAT improves adversarial training by smoothing the loss landscape through curriculum learning.

A new restart criterion for k-means++ improves clustering quality and adapts to data difficulty.

Symmetry in inverse problems leads to multiple solutions, but breaking symmetry helps deep learning.

New CTRL algorithm adapts to varying problem difficulty.

Corrects a flawed proof of the Kropholler Conjecture.

One of the central difficulties of settling the $L^2$-bounded curvature conjecture for the Einstein -Vacuum equations is to be able to control the causal structure of spacetimes with such limited regularity. In this paper we show how to circumvent this difficulty by showing that the geometry of null hypersurfaces of En…

We prove that the set of symplectic lattices in the Siegel space $\mathfrak{h}_g$ whose systoles generate a subspace of dimension at least 3 in $\mathbb{R}^{2g}$ does not contain any $\mathrm{Sp}(2g,\mathbb{Z})$-equivariant deformation retract of $\mathfrak{h}_g$.

Item Response Theory (IRT) aims to assess latent abilities of respondents based on the correctness of their answers in aptitude test items with different difficulty levels. In this paper, we propose the $β^3$-IRT model, which models continuous responses and can generate a much enriched family of Item Characteristic Cur…

Proposes PIC and POIC for measuring task difficulty in RL.

New algorithms handle heavy-tailed rewards in reinforcement learning.

Study shows perceptual boost of visual attention varies with task difficulty and size.

This work builds the connection between the regularity theory of optimal transportation map, Monge-Ampère equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse. According to the regularity theory of Monge-Ampère equation, if the support of the …

This work embeds annotations into a multidimensional space to measure classification difficulty.

In this work, we introduce the concept of bandlimiting into the theory of machine learning because all physical processes are bandlimited by nature, including real-world machine learning tasks. After the bandlimiting constraint is taken into account, our theoretical analysis has shown that all practical machine learnin…

Deep reinforcement learning has recently gained a focus on problems where policy or value functions are independent of goals. Evidence exists that the sampling of goals has a strong effect on the learning performance, but there is a lack of general mechanisms that focus on optimizing the goal sampling process. In this …

Increasingly complex generative models are being used across disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to evaluate the likelihood function and thus to perform likelihood-based statistical inference. A likelihood-free…

New method learns optimal environment and goal difficulty for reinforcement learning.

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction of deep reinforcement learning, which has greatly increased the difficulty of tas…