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.
Petridish efficiently searches neural architectures by iteratively adding shortcut connections.
Beam search improves feature selection for better model performance.
Paper introduces FoMoH for optimization without backpropagation.
Reverse annealing boosts quantum matrix factorization performance.
Audit financial machine learning workflows to detect spurious predictability.
Local search improves GFlowNets' ability to generate high-reward samples.
For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differentiable NAS solution, where the search space includes arbitrary feed-forward network consisting of the predefined number of connections. Be…
One-shot neural architecture search limits depth search space and prunes networks for better performance and uncertainty.
Deep Neural Networks(DNNs) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory is physically finite, which limits the image resolutions and batch sizes that could be used in training for better DNN performance. Unlike solutions that require physically upgrade GPUs, the G…
Proposes a new method to learn representations directly optimized for a task.
NASP uses proximal gradient descent to speed up neural architecture search.
New method designs multilayer nanoparticles using AI.
Portfolio diversification and active risk management are essential parts of financial analysis which became even more crucial (and questioned) during and after the years of the Global Financial Crisis. We propose a novel approach to portfolio diversification using the information of searched items on Google Trends. The…
We present experiments demonstrating that some other form of capacity control, different from network size, plays a central role in learning multilayer feed-forward networks. We argue, partially through analogy to matrix factorization, that this is an inductive bias that can help shed light on deep learning.
We combine forward investment performance processes and ambiguity averse portfolio selection. We introduce the notion of robust forward criteria which addresses the issues of ambiguity in model specification and in preferences and investment horizon specification. It describes the evolution of time-consistent ambiguity…
Recent works have highlighted the strength of the Transformer architecture on sequence tasks while, at the same time, neural architecture search (NAS) has begun to outperform human-designed models. Our goal is to apply NAS to search for a better alternative to the Transformer. We first construct a large search space in…
CPS solves inverse problems using forward passes and constrained particle seeking.
FDS tackles long horizon hyperparameter optimization issues.
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recent…
New method predicts and optimizes test-time scaling for LLMs.
I consider unsupervised extensions of the fast stepwise linear regression algorithm \cite{efroymson1960multiple}. These extensions allow one to efficiently identify highly-representative feature variable subsets within a given set of jointly distributed variables. This in turn allows for the efficient dimensional reduc…
Efficient neural network optimization reduces costs and improves model performance.
This work optimizes neural network bit-width and layer-width for efficiency.
RL improves combinatorial optimization by automating heuristic search.
Paper analyzes neural network complexity for planning problems.
Learning customer preferences from an observed behaviour is an important topic in the marketing literature. Structural models typically model forward-looking customers or firms as utility-maximizing agents whose utility is estimated using methods of Stochastic Optimal Control. We suggest an alternative approach to stud…
Discovering new physical products and processes often demands enormous experimentation and expensive simulation. To design a new product with certain target characteristics, an extensive search is performed in the design space by trying out a large number of design combinations before reaching to the target characteris…
Algorithm learns Bayesian network structure efficiently from data.
This paper defines less discriminatory algorithms and explores their feasibility.
A new framework predicts hidden Markov model regimes online.
Paper learns dictionaries for sparse signal recovery using automatic differentiation.
GTNs generate training data to accelerate AI learning.
The paper tackles model misspecification in reinforcement learning through a bootstrapped neural network and error correction.
Assessing heterogeneous treatment effects has become a growing interest in advancing precision medicine. Individualized treatment effects (ITE) play a critical role in such an endeavor. Concerning experimental data collected from randomized trials, we put forward a method, termed random forests of interaction trees (RF…
Study uses AI and ML to predict and optimize corrosion resistance of aluminum alloys.
Efficient implicit differentiation for Lasso hyperparameter optimization.
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In…
Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted first-order rules which act as templates for constructing feed-forward neural networks. While previous work has shown that using LRNNs can lead to state-of-the-art results in various ILP tasks, these results depended on hand-crafted ru…
The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward …
New method for dynamic valuation in markets with random endowments.
Independent component analysis (ICA) aims at decomposing an observed random vector into statistically independent variables. Deflation-based implementations, such as the popular one-unit FastICA algorithm and its variants, extract the independent components one after another. A novel method for deflationary ICA, referr…
In this paper, we consider signal detection algorithms in a multiple-input multiple-output (MIMO) decode-forward (DF) relay channel with one source, one relay, and one destination. The existing suboptimal near maximum likelihood (NML) detector and the NML with two-level pair-wise error probability (NMLw2PEP) detector a…
This paper shows how forward rate interpolations are equivalent to discount factor interpolations in yield curve construction.
Paper explores volatility swaps in rough volatility models.
MEC-IP uses IP to efficiently find MECs in BNs from observational data.
Stochastic SGN method converges faster than SGD for DNNs.
Proposes a link between randomness and compression in deep learning.
Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify it. With potential applications including perception modules and end-t…