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.
Study discovers patterns in insulin needs for T1D patients.
Deep RL improves blood glucose control for T1D patients.
Framework generates personalized insulin treatment strategies using deep models.
New model predicts blood glucose in diabetics with improved accuracy.
Reinforcement Learning improves insulin bolus decisions for type-I diabetes patients.
Machine learning detects subtle glucose changes for early diabetes diagnosis.
Paper uses imitation learning to create efficient insulin policies from MPC demonstrations.
HAD-Net forecasts glucose levels with insights into insulin and carbs diffusion.
\begin{abstract} We model individual T2DM patient blood glucose level (BGL) by stochastic process with discrete number of states mainly but not solely governed by medication regimen (e.g. insulin injections). BGL states change otherwise according to various physiological triggers which render a stochastic, statisticall…
Patients with Type I Diabetes (T1D) must take insulin injections to prevent the serious long term effects of hyperglycemia - high blood glucose (BG). Patients must also be careful not to inject too much insulin because this could induce hypoglycemia (low BG), which can potentially be fatal. Patients therefore follow a …
Neural system optimizes glucose levels in diabetics.
New model predicts multiple outputs with missing labels.
Paper proposes a DRL-based controller for networked AP systems that reduces communication frequency.
Study robust best-arm identification in linear bandits with lower bounds and algorithms.
Paper presents estimators for entropy and information in probabilistic models.
A method models continuous-time glucose distributions in children with diabetes.
Hybrid model learns interpretable meal-level glycemic control.
Modern treatments for Type 1 diabetes (T1D) use devices known as artificial pancreata (APs), which combine an insulin pump with a continuous glucose monitor (CGM) operating in a closed-loop manner to control blood glucose levels. In practice, poor performance of APs (frequent hyper- or hypoglycemic events) is common en…
RETAIN model improves glucose forecasting for diabetics, offering both accuracy and interpretability.
CBDL uses credal sets to improve uncertainty quantification in deep learning.
Economics does not need a scientific revolution. Economics needs accurate measurements according to high standards of natural sciences and meticulous work on revealing empirical relationships between measured variables.
New study shows neural networks need many samples for training.
Framework optimizes targeting high-need individuals while estimating treatment effects.
The paper examines when importance weighting is needed for nonparametric and misspecified models.
Study uses chatbot to understand users' needs for ML model explanations.
I argue that the current financial crisis highlights the crucial need of a change of mindset in economics and financial engineering, that should move away from dogmatic axioms and focus more on data, orders of magnitudes, and plausible, albeit non rigorous, arguments.
Using unknotting number, we introduce a link diagram invariant of Hass and Nowik type, which changes at most by 2 under a Reidemeister move. As an application, we show that a certain infinite sequence of diagrams of the trivial two-component link need quadratic number of Reidemeister moves for being unknotted with resp…
For each prime p > 7 we obtain the expression for an upper bound on the minimum number of colors needed to non-trivially color T(2, p), the torus knots of type (2, p), modulo p. This expression is t + 2 l -1 where t and l are extracted from the prime p. It is obtained from iterating the so-called Teneva transformations…
Develops a two-stage conformal prediction method for Parkinson's disease medication needs.
Bayesian Networks (BNs) are useful tools giving a natural and compact representation of joint probability distributions. In many applications one needs to learn a Bayesian Network (BN) from data. In this context, it is important to understand the number of samples needed in order to guarantee a successful learning. Pre…
Improves neural network estimates using IFs without needing more data.
This paper is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We assume no math knowledge beyond what you learned in calculus 1, and provide links to help you refresh the necessary math where needed. Note that you do not need to understand this materia…
Due to recent technological developments, Machine Learning (ML), a subfield of Artificial Intelligence (AI), has been successfully used to process and extract knowledge from a variety of complex problems. However, a thorough ML approach is complex and highly dependent on the problem at hand. Additionally, implementing …
Computational limitations require more model parameters for robust learning.
The article examines how many stabilizations are needed to transform 5D s-cobordisms into product cobordisms.
Paper finds how many neurons are needed to approximate histogram distributions.
Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning problems in classification, regression, and fine-tuning of policy gradients in reinf…
A survey of existing methods for stopping active learning (AL) reveals the needs for methods that are: more widely applicable; more aggressive in saving annotations; and more stable across changing datasets. A new method for stopping AL based on stabilizing predictions is presented that addresses these needs. Furthermo…
We prove two theorems on the removal of singularities on the boundary of a pseudo-holomorphic curve. In one theorem, we need no apriori assumption on the area of the curve. The proof uses a doubling argument with the goal of converting curves with boundary to curves without boundary. Our method is new and geometric and…
New formula for rotation number without needing a base point.
If a rectangular diagram represents the trivial knot, then it can be deformed into the trivial rectangular diagram with only four edges by a finite sequence of merge operations and exchange operations, without increasing the number of edges, which was shown by I. A. Dynnikov. Using this, Henrich and Kauffman gave an up…
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…
With the increasing availability of AI-based decision support, there is an increasing need for their certification by both AI manufacturers and notified bodies, as well as the pragmatic (real-world) validation of these systems. Therefore, there is the need for meaningful and informative ways to assess the performance o…
Algorithms learned from data are increasingly used for deciding many aspects in our life: from movies we see, to prices we pay, or medicine we get. Yet there is growing evidence that decision making by inappropriately trained algorithms may unintentionally discriminate people. For example, in automated matching of cand…
SGD's performance improves with critical batch size, minimizing SFO complexity.
The radius of the star-shaped set need not have been continuous.
Express Wavenet is an improved optical diffractive neural network. At each layer, it uses wavelet-like pattern to modulate the phase of optical waves. For input image with n2 pixels, express wavenet reduce parameter number from O(n2) to O(n). Only need one percent of the parameters, and the accuracy is still very high.…
We study an economic model where agents trade a variety of products by using one of three competing rules: "need", "greed" and "noise". We find that the optimal strategy for any agent depends on both product composition in the overall market and composition of strategies in the market. In particular, a strategy that do…