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.
This study investigates abrupt learning dynamics in Transformers, revealing plateau formation and internal representation collapse.
Telescope detects LLM generated text by measuring token repetition probability.
Generative model captures repetitive industrial processes with varying durations and dynamics.
This paper considers the problem of characterizing the simplest discrete point sets that are aperiodic, using invariants based on topological dynamics. A Delone set whose patch-counting function N(T), for radius T, is finite for all T is called repetitive if there is a function M(T) such that every ball of radius M(T)+…
UTE improves reinforcement learning by measuring action uncertainty, enhancing policy learning efficiency.
Recurrent models can produce infinite sequences, causing bias; new methods prevent this.
Spaced repetition is a technique for efficient memorization which uses repeated, spaced review of content to improve long-term retention. Can we find the optimal reviewing schedule to maximize the benefits of spaced repetition? In this paper, we introduce a novel, flexible representation of spaced repetition using the …
How does one find dimensions in multivariate data that are reliably expressed across repetitions? For example, in a brain imaging study one may want to identify combinations of neural signals that are reliably expressed across multiple trials or subjects. For a behavioral assessment with multiple ratings, one may want …
The paper uses persistent homology to estimate recurrence times in multi-variate time series.
Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.
A new neural network separates vocals from music accompaniment.
This work uses QPGPs to improve ILC performance in repetitive tasks.
Game aims to improve social interactions for teenagers with ASD.
Bayesian optimization outperforms other methods in hyperparameter tuning for reinforcement learning.
Experimental design is a classical statistics problem and its aim is to estimate an unknown -dimensional vector from linear measurements where a Gaussian noise is introduced in each measurement. For the combinatorial experimental design problem, the goal is to pick out of the given experiments so as to m…
Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parameters iteratively. However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels. In this p…
Data repetition improves SGD's learning of high-dimensional functions.
Estimates linear model from noisy covariates and instruments using spectral regularization.
X-ray free-electron lasers (XFELs) are the only sources currently able to produce bright few-fs pulses with tunable photon energies from 100 eV to more than 10 keV. Due to the stochastic SASE operating principles and other technical issues the output pulses are subject to large fluctuations, making it necessary to char…
Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some post-hoc fixes have been proposed, in particular top- and nucleus sampling, they …
Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead to the generation of inappropriate, biased, or offensive text. Reinforcement Lear…
We study the effect of impairment on stochastic multi-armed bandits and develop new ways to mitigate it. Impairment effect is the phenomena where an agent only accrues reward for an action if they have played it at least a few times in the recent past. It is practically motivated by repetition and recency effects in do…
Prior work on training generative Visual Dialog models with reinforcement learning(Das et al.) has explored a Qbot-Abot image-guessing game and shown that this 'self-talk' approach can lead to improved performance at the downstream dialog-conditioned image-guessing task. However, this improvement saturates and starts d…
Riemannian manifolds can be realized as leaf spaces of matchbox manifolds.
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
Characterizes Milnor invariants with limited repetitions.
ADMMiRNN solves RNN training issues with stable convergence.
Spaced repetition is among the most studied learning strategies in the cognitive science literature. It consists in temporally distributing exposure to an information so as to improve long-term memorization. Providing students with an adaptive and personalized distributed practice schedule would benefit more than just …
Automatic conflict detection has grown in relevance with the advent of body-worn technology, but existing metrics such as turn-taking and overlap are poor indicators of conflict in police-public interactions. Moreover, standard techniques to compute them fall short when applied to such diversified and noisy contexts. W…
In online display advertising, selecting the most effective ad creative (ad image) for each impression is a crucial task for DSPs (Demand-Side Platforms) to fulfill their goals (click-through rate, number of conversions, revenue, and brand improvement). As widely recognized in the marketing literature, the effect of ad…
This work addresses the problem of segmentation in time series data with respect to a statistical parameter of interest in Bayesian models. It is common to assume that the parameters are distinct within each segment. As such, many Bayesian change point detection models do not exploit the segment parameter patterns, whi…
One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on human…
Project infinite time series graphs to finite marginal models using number theory.
There has been considerable growth and interest in industrial applications of machine learning (ML) in recent years. ML engineers, as a consequence, are in high demand across the industry, yet improving the efficiency of ML engineers remains a fundamental challenge. Automated machine learning (AutoML) has emerged as a …
In this paper we consider the problem of clustering collections of very short texts using subspace clustering. This problem arises in many applications such as product categorisation, fraud detection, and sentiment analysis. The main challenge lies in the fact that the vectorial representation of short texts is both hi…
EB-RANSAC uses energy-based model for robust estimation without complex sampling.
Humans are capable of building holistic representations for images at various levels, from local objects, to pairwise relations, to global structures. The interpretation of structures involves reasoning over repetition and symmetry of the objects in the image. In this paper, we present the Program-Guided Image Manipula…
This study is a detailed analysis of Speculation Game, a minimal agent-based model of financial markets, in which the round-trip trading and the dynamic wealth evolution with variable trading volumes are implemented. Instead of herding behavior, we find that the emergence of volatility clustering can be induced by the …
Research shows bias in machine learning can be due to algorithmic flaws, not just data.
Predicts local AQI using mobile sensor data, improving accuracy by 71.654 MSE.
Financial LLMs need explicit bias consideration to avoid invalid results.
OpenGM is a C++ template library for defining discrete graphical models and performing inference on these models, using a wide range of state-of-the-art algorithms. No restrictions are imposed on the factor graph to allow for higher-order factors and arbitrary neighborhood structures. Large models with repetitive struc…
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an inductive bias in gradient descent methods that results in the overestimation of the…
It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (R…
Mitigates gender bias amplification in model predictions.
Iterative method learns unknown constraints for MPC control.
Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models consisting of an encoder model to produce a hidden representation o…
Depth uncertainty networks don't improve with bias correction, contrary to expectations.