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 finds real-world datasets contain natural experiments that can improve model performance.
Natural experiment dataset reveals inconsistent treatment effect estimators.
Square-root natural-gradient improves variational inference convergence.
A new test improves statistical inference in bandit algorithms without sacrificing adaptiveness.
iPrompt uses LLMs to generate natural-language explanations of data patterns.
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
Probabilistic active meta-learning improves data efficiency in robotics.
RL optimizes resource allocation in MG by balancing experience and exploration.
Paper discusses new stochastic algorithms for sparse signal recovery.
PixL2R maps natural language to pixel-based rewards for RL, improving sample efficiency.
New method minimizes experiment cost while maintaining accuracy.
Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample inefficient. A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the ag…
Automated PDE discovery from multiple noisy experiments.
Motivated by the widespread adoption of large-scale A/B testing in industry, we propose a new experimentation framework for the setting where potential experiments are abundant (i.e., many hypotheses are available to test), and observations are costly; we refer to this as the experiment-rich regime. Such scenarios requ…
DeFi doesn't fully remove trust, showing run risk and personal character's importance.
New insights into experience replay in RL algorithms.
We introduce a novel definition of curvature for hypergraphs, a natural generalization of graphs, by introducing a multi-marginal optimal transport problem for a naturally defined random walk on the hypergraph. This curvature, termed \emph{coarse scalar curvature}, generalizes a recent definition of Ricci curvature for…
This work investigates uncertainty quantification for black-box large language models in natural language generation.
Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However, most of them have focused on binary sentiment classification. In this paper, we u…
Develops an efficient method for large-scale deep learning problems.
The paper proposes a method to train time-varying generative models using natural gradients.
DDPM encoder matches optimal transport for natural images.
Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP: a new method for sparse structured inference, and its natural loss function. SparseMAP automatically selects only a few global structures: it is situated between MAP inference, which picks a single …
Algorithm selects optimal experiments in Markov chains to learn unknown quantities.
MuLan links music audio to natural language tags.
Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respe…
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learnin…
A-ICP selects experiments to learn causal effects efficiently.
It is well known that in stochastic multi-armed bandits (MAB), the sample mean of an arm is typically not an unbiased estimator of its true mean. In this paper, we decouple three different sources of this selection bias: adaptive \emph{sampling} of arms, adaptive \emph{stopping} of the experiment, and adaptively \emph{…
Functional Magnetic Resonance Imaging (fMRI) provides dynamical access into the complex functioning of the human brain, detailing the hemodynamic activity of thousands of voxels during hundreds of sequential time points. One approach towards illuminating the connection between fMRI and cognitive function is through dec…
A method for disentangling text representations without supervision.
BICauseTree improves causal effect estimation by identifying clusters and balancing treatment allocation.
Natural gradient has been recently introduced to the field of boosting to enable the generic probabilistic predication capability. Natural gradient boosting shows promising performance improvements on small datasets due to better training dynamics, but it suffers from slow training speed overhead especially for large d…
The techniques of deep learning have become the state of the art methodology for executing complicated tasks from various domains of computer vision, natural language processing, and several other areas. Due to its rapid development and promising benchmarks in those fields, researchers started experimenting with this t…
In this paper, we study the design and analysis of experiments conducted on a set of units over multiple time periods where the starting time of the treatment may vary by unit. The design problem involves selecting an initial treatment time for each unit in order to most precisely estimate both the instantaneous and cu…
NRWS improves training of SBNs and HMs using natural gradient.
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate th…
Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten ta…
SSMBA generates synthetic data to improve robustness in natural language tasks.
Conformal prediction fails under severe feature turnover in COVID-19 supply chain tasks.
Active learning improves neutron spectroscopy experiments by automating measurement selection.
Proposes model-based robust deep learning to handle natural variation in data.
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…
Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accu…
Robust tensor CP decomposition involves decomposing a tensor into low rank and sparse components. We propose a novel non-convex iterative algorithm with guaranteed recovery. It alternates between low-rank CP decomposition through gradient ascent (a variant of the tensor power method), and hard thresholding of the resid…
A new algorithm for training generative models using Sinkhorn divergence.
3D models vulnerable to adversarial attacks, new method improves success rate and naturalness.
LLMs are compared to Markov chains for natural language processing.