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.
Develops a generic approach for stable model distillation.
This paper examines the stability of learned explanations for black-box predictions via model distillation with decision trees. One approach to intelligibility in machine learning is to use an understandable `student' model to mimic the output of an accurate `teacher'. Here, we consider the use of regression trees as a…
Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teacher model and a student model, and penalize predictions under different perturbations by a consistency constraint. However, the weights of the…
New method improves generative modeling on convex domains using regularized mirror maps and Student-t priors.
The paper proposes a machine learning framework for portfolio optimization with limited data.
This study analyzes counterfactual explanations for student success models.
The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.
Student performance modelling (SPM) is a critical step to assessing and improving students performances in their learning discourse. However, most existing SPM are based on statistical approaches, which on one hand are based on probability, depicting that results are based on estimation; and on the other hand, actual i…
Predicts student performance in interactive online question pools using GNNs.
Contributions: Prior studies on education have mostly followed the model of the cross sectional study, namely, examining the pretest and the posttest scores. This paper shows that students' knowledge throughout the intervention can be estimated by time series analysis using a hidden Markov model. Background: Analyzing …
We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, i…
Modeling student behaviors and multiple predictions for early intervention.
Bayesian model identifies skill difficulties and student subgroups in engineering education.
Pea-KD improves BERT student models by 4.4% on average in GLUE tasks.
In recent years, distance education has enjoyed a major boom. Much work at The Open University (OU) has focused on improving retention rates in these modules by providing timely support to students who are at risk of failing the module. In this paper we explore methods for analysing student activity in online virtual l…
Proposes RaT to mitigate bias in student-teacher estimation.
Distilled models often fail to match teacher models, despite improving generalization.
Each year, roughly 30% of first-year students at US baccalaureate institutions do not return for their second year and over $9 billion is spent educating these students. Yet, little quantitative research has analyzed the causes and possible remedies for student attrition. Here, we describe initial efforts to model stud…
Improved learning to reweight using deep interactions between student and teacher models.
Enhances student diversity in collaborative learning.
Estimates model performance from compute budget for distillation.
Proposes new models to predict student grades more accurately.
Two-layer ReLU networks outperform kernel methods in teacher-student settings.
We use official data for all 16 federal German states to study the causal effect of a flat 1000 Euro state-dependent university tuition fee on the enrollment behavior of students during the years 2006-2014. In particular, we show how the variation in the introduction scheme across states and times can be exploited to i…
A new KD layer lets student models learn and apply teacher knowledge explicitly.
An important, yet largely unstudied, problem in student data analysis is to detect misconceptions from students' responses to open-response questions. Misconception detection enables instructors to deliver more targeted feedback on the misconceptions exhibited by many students in their class, thus improving the quality…
A new method for student-initiated action advice using novelty detection.
Study predicts academic achievement using students' support networks.
Improved image reconstruction using VAEs with Student's t-prior.
Bayesian neural networks approximate Student-t processes in the infinite-width limit.
Develops a fair post-processing method for student success predictions.
Motivation: Biomarker discovery from high-dimensional data is a crucial problem with enormous applications in biology and medicine. It is also extremely challenging from a statistical viewpoint, but surprisingly few studies have investigated the relative strengths and weaknesses of the plethora of existing feature sele…
One of the important measures of quality of education is the performance of students in the academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and how to improve their performance ahead of time using data mining…
Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course pr…
Self-training with noisy student-teacher boosts keyword spotting accuracy.
Paper generalizes teacher-student model for realistic data.
Method teaches students without teachers, estimating true labels from crowdsourcing.
A new training method improves MLIPs for faster, lighter simulations.
Proposes a new Bayesian mixture of student-t processes for modeling non-stationary data.
New metric MADD assesses fairness of predictive student models.
E-learning systems are capable of providing more adaptive and efficient learning experiences for students than the traditional classroom setting. A key component of such systems is the learning strategy, the algorithm that designs the learning paths for students based on information such as the students' current progre…
KT models struggle with student concept drift, but BKT remains the most stable.
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…
KT models improved slightly with synthetic student data.
We investigate the Student-t process as an alternative to the Gaussian process as a nonparametric prior over functions. We derive closed form expressions for the marginal likelihood and predictive distribution of a Student-t process, by integrating away an inverse Wishart process prior over the covariance kernel of a G…
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robu…
New model shows weak teachers can help strong students learn even with imperfect labels.
Knowledge tracing is a sequence prediction problem where the goal is to predict the outcomes of students over questions as they are interacting with a learning platform. By tracking the evolution of the knowledge of some student, one can optimize instruction. Existing methods are either based on temporal latent variabl…