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.
Optimizes contrastive learning with individualized temperatures for better performance on imbalanced datasets.
problem The common practice of using a global temperature parameter ignores the varying semantic similarity across different anchor data.
method Proposes a new robust contrastive loss inspired by distributionally robust optimization (DRO) and an efficient stochastic algorithm for automatic temperature individualization.
result Our method automatically learns a suitable temperature for each sample, improving performance on imbalanced datasets.
HET-XL improves heteroscedastic classifiers for large-scale image classification.
problem Scaling heteroscedastic classifiers to handle large numbers of classes and tuning the temperature hyperparameter.
method HET-XL, a heteroscedastic classifier with independent parameter count from the number of classes, learns the temperature hyperparameter directly from training data.
result HET-XL requires 14X fewer additional parameters and performs better than baseline heteroscedastic classifiers on large image classification datasets.
A new space-time model for interacting agents on the financial market is presented. It is a combination of the Curie-Weiss model and a space-time model introduced by Järpe 2005. Properties of the model are derived with focus on the critical temperature and magnetization. It turns out that the Hamiltonian is a sufficien…
Hyperfitting improves LLM generation quality by enhancing diversity, contrary to simple temperature scaling.
problem Improving open-ended generation quality of LLMs with minimal fine-tuning effort.
method Demonstrates that hyperfitting, a phenomenon where LLMs are fine-tuned to near-zero training loss, enhances generation quality and mitigates repetition.
result Hyperfitting is distinct from temperature scaling and involves a dynamic, context-dependent rank reordering mechanism in the final transformer block.
We develop a variant of multiclass logistic regression that is significantly more robust to noise. The algorithm has one weight vector per class and the surrogate loss is a function of the linear activations (one per class). The surrogate loss of an example with linear activation vector a and class c has t…
Weather is a key production factor in agricultural crop production and at the same time the most significant and least controllable source of peril in agriculture. These effects of weather on agricultural crop production have triggered a widespread support for weather derivatives as a means of mitigating the risk assoc…
We applied Dirac distribution, Bose-Einstein distribution, and occasionally Boltzmann-Gibbs distribution in order to determine which is optimal for income distribution on a large pool of countries. The best fit to the data was observed in the case of Fermi-Dirac distribution, for which the coefficient of determination …
Variational inference (VI) combined with data subsampling enables approximate posterior inference over large data sets, but suffers from poor local optima. We first formulate a deterministic annealing approach for the generic class of conditionally conjugate exponential family models. This approach uses a decreasing te…
Theoretical understanding of how deep neural network (DNN) extracts features from input images is still unclear, but it is widely believed that the extraction is performed hierarchically through a process of coarse-graining. It reminds us of the basic concept of renormalization group (RG) in statistical physics. In ord…
We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non…
This paper measures temperature in agent systems using volatility.
problem How to measure temperature in agent systems.
method Examined an agent system with two decision options in a news environment, established the measurement equation, and outlined the concept of temperature measurement.
result Illustrated a strategy for influencing average opinion in competing subsystems.
Attention temperature improves robustness of ICL in high-dimensional settings.
problem ICL robustness failure under distribution shift in high dimensions.
method Analyzed a Transformer with approximate softmax attention, derived a closed-form error expression, and showed optimal temperature minimizes error.
result Optimal attention temperature minimizes ICL generalization error under distribution shift.
Trends in terrestrial temperature variability are perhaps more relevant for species viability than trends in mean temperature. In this paper, we develop methodology for estimating such trends using multi-resolution climate data from polar orbiting weather satellites. We derive two novel algorithms for computation that …
The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has been very popular in machine learning due to its "Occam's razor" interpretation. Unfortunately, calculating the potentials in the maximum-entro…