arXiv research

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

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

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 (…

In multi-task learning, difficulty levels of different tasks are varying. There are many works to handle this situation and we classify them into five categories, including the direct sum approach, the weighted sum approach, the maximum approach, the curriculum learning approach, and the multi-objective optimization ap…

Topic discovery has witnessed a significant growth as a field of data mining at large. In particular, time-evolving topic discovery, where the evolution of a topic is taken into account has been instrumental in understanding the historical context of an emerging topic in a dynamic corpus. Traditionally, time-evolving t…

StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-acti…

Transformers learn to adapt to different task difficulties and resist distribution shifts.

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 …

Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being explainable. In this paper, we propose Deep-IRT which is a synthesis of the item res…

TS-Fault benchmarks TSF models against structural faults.

Constructs metrics with Q-curvature on manifolds with singularities.

Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels. When R…

The paper studies estimating the normalizing constant using queries to a black-box function in RKHS.

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…

In this paper, we study the motion of level sets by general curvature. The difficulty of this setting is that a general curvature function is only well defined in an admissible cone. In order to extend the existence of a weak solution of a general curvature flow to outside the cone we introduce a new approximation func…

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…

Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…

Bayesian model identifies skill difficulties and student subgroups in engineering education.

Adaptive coverage policies improve conformal prediction accuracy.

New CTRL algorithm adapts to varying problem difficulty.

BiDVL improves EBLVMs for visual tasks by optimizing two variational distributions.

New metrics predict human sentence comprehension across languages.

Music FaderNets learns high-level musical qualities from low-level attributes.

ART adapts class-wise resampling to improve imbalanced classification performance.

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obst…

Fault detection problem for closed loop uncertain dynamical systems, is investigated in this paper, using different deep learning based methods. Traditional classifier based method does not perform well, because of the inherent difficulty of detecting system level faults for closed loop dynamical system. Specifically, …

We propose a deep learning strategy to estimate the mean curvature of two-dimensional implicit interfaces in the level-set method. Our approach is based on fitting feed-forward neural networks to synthetic data sets constructed from circular interfaces immersed in uniform grids of various resolutions. These multilayer …

New algorithm solves complex optimization problems efficiently.

The paper introduces an adjacency constraint to improve goal-conditioned HRL.

Paper proposes a perfect-fit model for CDO tranches.

Estimating the difficulty level of math word problems is an important task for many educational applications. Identification of relevant and irrelevant sentences in math word problems is an important step for calculating the difficulty levels of such problems. This paper addresses a novel application of text categoriza…

Insects play such a crucial role in ecosystems that a shift in demography of just a few species can have devastating consequences at environmental, social and economic levels. Despite this, evaluation of insect demography is strongly limited by the difficulty of collecting census data at sufficient scale. We propose a …

A new method for solving complex sequential decision-making problems by decomposing them into multiple levels.

SLIM model tackles graph classification by resolving part-interaction dilemmas.

Book introduces principles of LCK geometry for complex manifold students.

This study compares machine learning methods for high-cardinality categorical variables.

mmFall detects falls using mmWave radar and a hybrid VRAE, achieving high accuracy.

This paper explores the suitability of using automatically discovered topics from MOOC discussion forums for modelling students' academic abilities. The Rasch model from psychometrics is a popular generative probabilistic model that relates latent student skill, latent item difficulty, and observed student-item respons…

New model corrects bias in crowdsourced ratings for diverse items.

Single-stage neural architecture improves text-to-image synthesis.

Study shows code-level optimizations significantly impact deep RL algorithms.

Effective riverine flood forecasting at scale is hindered by a multitude of factors, most notably the need to rely on human calibration in current methodology, the limited amount of data for a specific location, and the computational difficulty of building continent/global level models that are sufficiently accurate. M…

Proposes $β^{4}$-IRT, a new IRT model with enhanced discrimination estimation.

We prove rigidity for hypersurfaces with boundary in the unit $(n+1)$-sphere with scalar curvature bounded below by $n(n-1)$. Under appropriate boundary conditions, the hypersurfaces are shown to be part of the equatorial spheres. The lower bound $n(n-1)$ is critical in the sense that the hypersurface may contain geode…

AER dynamically adjusts entropy regularization for better LLM reinforcement learning.

This report contains the details regarding our submission to the OffensEval 2019 (SemEval 2019 - Task 6). The competition was based on the Offensive Language Identification Dataset. We first discuss the details of the classifier implemented and the type of input data used and pre-processing performed. We then move onto…

PatchGT uses non-trainable graph patches to improve graph representation learning.

Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrat…