Model shows loss curve with two distinct exponents due to sparse activations.
problem Sparse activations impact neural network scaling laws.
method Introduced a model for neural scaling laws under sparse activations, derived asymptotic population loss, and analyzed gradient-descent dynamics.
result Loss curve exhibits double-descent peak near interpolation threshold with two distinct scaling exponents.
Chinchilla Approach 2 biases neural scaling law estimates, leading to unnecessary compute costs.
problem Systematic biases in Chinchilla Approach 2's parabolic fits of neural scaling laws.
method Analyzes three sources of error: IsoFLOP sampling grid width, uncentered sampling, and loss surface asymmetry.
result Chinchilla Approach 3 largely eliminates these biases, offering a more convenient or scalable alternative.
Review of modern computational optimal transport methods for biomedical applications.
problem Efficient computation of optimal transport for big data.
method Regularization-based and projection-based computational methods.
result Advancements in computational optimal transport methods for biomedical research.
New tools quantify deep generative models' performance.
problem Measuring the quality-diversity trade-off in deep generative models.
method Established non-asymptotic bounds on sample complexity and introduced frontier integrals.
result Smoothed estimators improve convergence rates of divergence frontiers.
New scaling laws optimize model size, training, and inference for better performance.
problem Trade-off between model size and inference cost in modern LLMs.
method Train-to-Test (T2) scaling laws that jointly optimize model size, training tokens, and inference samples. result Optimal pretraining decisions shift into overtraining regime, leading to stronger performance.
Neural network approximates weakly efficient frontier of convex vector optimization problems.
problem Approximating the weakly efficient frontier of convex vector optimization problems.
method Designing a neural network architecture to approximate the weakly efficient frontier of convex vector optimization problems (CVOP) satisfying Slater's condition.
result The proposed algorithm effectively approximates the true weakly efficient frontier of CVOPs, even for large problems.
Efficiently computes optimal transport maps and Wasserstein barycenters using conditional normalizing flows.
problem Computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces.
method Uses conditional normalizing flows to approximate distributions and solve the primal problem.
result Shows computational feasibility for hundreds of input distributions and yields accurate results.
Quantum computing optimizes ESG portfolios efficiently.
problem Optimizing investment portfolios with risk, return, and ESG considerations.
method Formulated discrete Markowitz portfolio theory (DMPT) for quantum annealers, incorporating ESG ratings.
result Discrete portfolios converge to continuous solutions as budgets increase, outperforming traditional methods.
A new method for multi-objective Bayesian optimization using entropy search and variational lower bound maximization.
problem Efficiently optimizing multiple objectives in continuous domains.
method Approximates the Pareto-frontier using a mixture distribution and optimizes the balance through variational lower bound maximization.
result Demonstrated effectiveness especially with many objective functions.
Algorithm maps trade-off between clustering fidelity and representation size.
problem Optimizing trade-off between clustering fidelity and representation size.
method Introduces primal Deterministic Information Bottleneck (DIB) problem for discrete search spaces.
result Shows richer Pareto frontier over Lagrangian relaxation.
A power-law fit to the empirical inference-compute frontier in LOB prediction suggests a scaling-law-style frontier.
problem Limit order book prediction
method Using a suite of models ranging from small decision trees to neural LOB architectures
result A power-law fit to the low- and mid-compute non-MLPLOB frontier extrapolates across multiple orders of magnitude and attains R2=0.941 on the excluded high-compute MLPLOB target frontier. Study optimizes compute usage for LLM web agents, improving performance.
problem High compute costs and narrow focus on single-step tasks limit LLM web agents.
method Two-stage pipeline: SFT followed by on-policy RL, with hyperparameter optimization.
result Combining SFT and on-policy RL requires 55% less compute to match peak SFT performance.
SignSGD outperforms SGD in linear regression with optimal scaling laws under PLRF model.
problem Improving linear regression performance with signSGD under power-law random features.
method Analysis of signSGD risk under PLRF model, comparison with SGD, identification of unique effects.
result SignSGD can have a steeper compute-optimal slope than SGD in noisy regimes, especially with WSD schedule.
The paper develops methods to estimate the high-dimensional efficient frontier without distributional assumptions.
problem Estimating the mean-variance efficient frontier in high-dimensional settings.
method Random matrix theory and asymptotic analysis for high-dimensional data.
result Developed consistent estimators for the mean, variance, and covariance of the efficient frontier.
GeMA learns latent manifolds to benchmark complex systems.
problem Benchmarking complex systems like rail networks and economies with classical methods.
method Geometric Manifold Analysis (GeMA) using a productivity-manifold variational autoencoder (ProMan-VAE).
result GeMA provides more nuanced efficiency evaluations in complex systems.
New research shows shrinkage methods re-scale portfolio efficient frontiers under distributional misspecification.
problem Poor performance of mean-variance portfolio decisions under distributional assumptions.
method Investigation of shrinkage methods under different distributional assumptions (auto-correlation, skewness, excess kurtosis).
result Shrinkage methods re-scale the sample efficient frontier, implying standard comparison methods are flawed.
Enhances hedging strategies using deep neural networks.
problem Optimizing risks and returns in financial hedging.
method Integrates deep neural networks and random forest classifiers to find optimal hedging strategies.
result Improved hedging strategies with lower costs and risks.
Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.
problem Understanding the tradeoff between fairness and accuracy in models serving multiple demographic groups.
method Characterizing the fairness-accuracy (FA) Pareto frontier, approximating it from limited data, and bounding the worst-case gap.
result Derivation of worst-case-optimal estimators and uniform finite-sample bounds for the entire FA frontier.
A new asset allocation model uses Markov states from clustered efficient frontier coefficients.
problem Characterizing market regimes using efficient frontiers for better asset allocation.
method Hierarchical clustering of monthly efficient frontier coefficients to define states, then a Markov process on these states for portfolio optimization.
result The model significantly outperforms benchmark portfolios empirically.
The p-index improves investment performance for NYSE stocks but not for SSE stocks.
problem Improving investment performance for stocks using the p-index.
method Comparing different p-ratio strategies and empirical efficient frontiers for SSE and NYSE stocks.
result The p-index enhances investment performance for NYSE stocks but not for SSE stocks.
The profitability of CPMMs is significantly impacted by mint and burn fees.
problem Understanding the profitability of decentralized exchanges.
method Formalized liquidity providers' profitability conditions, studied the effect of mint and burn fees, and compiled a large data set from Uniswap V2 transactions.
result The profitability of liquidity provision is severely affected by mint and burn costs.
We identify and optimize the fairness-accuracy tradeoff through TAF Curves and FAUC metrics.
problem Balancing fairness and accuracy in machine learning models for high-stakes decisions.
method Developed TAF Curves and FAUC metric to quantify the tradeoff, and introduced FairStacks framework to expand the Pareto frontier.
result FairStacks framework expands the empirical Pareto frontier and improves the FAUC for model ensembles.
P-Trees improve investment performance by optimizing the efficient frontier.
problem Optimizing investment performance in complex financial markets.
method Introducing P-Trees, a new tree-based model for analyzing panel data.
result P-Trees significantly advance the efficient frontier and outperform existing models.
A simplified model for fixed income portfolio optimisation.
problem Modeling interest rates and credit risk in fixed income portfolios.
method Proposes a two-factor model for the time evolution of the efficient frontier.
result The efficient frontier is mainly controlled by linear constraints, with standard deviation less important.
This paper presents an analysis of the study variables such as gdp, employment levels, the level of R & D and technology that will serve as the basis for stochastic modeling of production possibilities frontier in the goodness of fractal dimensions Ex Ante and Ex Post a priori to determine the levels of causality immed…
Model predicts neural network performance scaling laws across various factors.
problem Understanding the performance of neural networks across different training factors.
method Random feature model trained with gradient descent, analyzing compute-optimal scaling laws.
result Predicts asymmetric compute-optimal scaling rule and behavior of training and test loss gap.
Estimates model performance from compute budget for distillation.
problem Risk mitigation in large-scale distillation.
method Distillation scaling law based on compute budget allocation.
result Maximizes student performance with compute-optimal allocation.
Paper develops fast method for computing optimal transport.
problem Efficient computation of optimal transport distance between distributions.
method Entropy-regularized extragradient method for first-order optimization.
result Achieves state-of-the-art runtime guarantees and good numerical performance.
The paper introduces a machine learning method to forecast market direction using efficient frontier coefficients.
problem Improving asset return estimation for portfolio optimization.
method Monthly directional market forecast using an online decision tree trained on efficient frontier coefficients.
result The method outperforms baseline portfolios and other feature sets.
It is well established that in a market with inclusion of a risk-free asset the single-period mean-variance efficient frontier is a straight line tangent to the risky region, a fact that is the very foundation of the classical CAPM. In this paper, it is shown that in a continuous-time market where the risky prices are …
Differentiable relaxation for inferring partial orders from noisy linear data.
problem Inference of partial orders from linear data with noisy observations.
method Introducing a differentiable relaxation to model noisy linear extensions, replacing discontinuous precedence and feasibility with smooth surrogates.
result Smooth posterior that preserves partial-order semantics, supports gradient-based inference, and converges to hard likelihood.
Deep learning improves portfolio optimization efficiency.
problem Efficient frontier calculation in high-dimensional finance problems.
method Deep neural networks for portfolio optimization with added constraints.
result A new projected feedforward network outperforms classical methods.
Blockchain funds balance risk and return for various investors.
problem Creating diversified portfolios with risk parity for different risk appetites.
method Developed three funds (Alpha, Beta, Gamma) with distinct risk and return profiles, setting weights inversely proportional to risk.
result Blockchain enables investors to select their preferred risk-return combination and allocate wealth accordingly.
We consider the problem of finding the efficient frontier associated with the risk-return portfolio optimization model. We derive the analytical expression of the efficient frontier for a portfolio of N risky assets, and for the case when a risk-free asset is added to the model. Also, we provide an R implementation, an…
This note finds closed-form solutions for mean-risk portfolios using a specific type of mixture distribution.
problem Finding optimal portfolios under mean-risk criteria for general distributions.
method Using normal mean-variance mixture (NMVM) distributions, the paper derives closed-form expressions for mean-risk frontiers by optimizing a Markowitz model with adjusted return vectors.
result Closed-form solutions for mean-risk portfolios are found for return vectors following NMVM distributions.
New algorithm reduces regret in online portfolio and quantum state learning.
problem Efficiently learning portfolios and quantum states online with minimal regret.
method BISONS algorithm for online portfolio selection, SCHRODINGER'S BISONS for quantum states, with polylogarithmic regret.
result First efficient algorithm with polylogarithmic regret for online portfolio selection and quantum states.
Study optimizes fairness in predictive models by balancing utility and separation.
problem Balancing fairness and utility in predictive models.
method Information-theoretic approach using conditional mutual information (CMI).
result Reduces separation violations while maintaining or improving utility.
This paper studies an entropy-based multi-objective Bayesian optimization (MBO). The entropy search is successful approach to Bayesian optimization. However, for MBO, existing entropy-based methods ignore trade-off among objectives or introduce unreliable approximations. We propose a novel entropy-based MBO called Pare…
The paper tackles fair policy targeting by optimizing allocation rules to minimize unfairness.
problem Discrimination in individualized treatments of social welfare programs.
method Formulated as a mixed-integer linear program, solved using off-the-shelf algorithms, derived regret bounds and small sample guarantees.
result Designs fair and efficient treatment allocation rules within the Pareto frontier.
Domain Translation is the problem of finding a meaningful correspondence between two domains. Since in a majority of settings paired supervision is not available, much work focuses on Unsupervised Domain Translation (UDT) where data samples from each domain are unpaired. Following the seminal work of CycleGAN for UDT, …
Many domains of science have developed complex simulations to describe phenomena of interest. While these simulations provide high-fidelity models, they are poorly suited for inference and lead to challenging inverse problems. We review the rapidly developing field of simulation-based inference and identify the forces …
New phases identified in neural scaling laws with compute limits.
problem Understanding neural scaling laws under compute constraints.
method Solved neural scaling model with stochastic gradient descent, derived loss curves, analyzed model-parameter-count phases.
result Identified 4 phases (+3 subphases) in data-complexity/target-complexity phase-plane, derived exponents.
We propose a stochastic approximation method for approximating the efficient frontier of chance-constrained nonlinear programs. Our approach is based on a bi-objective viewpoint of chance-constrained programs that seeks solutions on the efficient frontier of optimal objective value versus risk of constraint violation. …
The paper proposes a method to ensure fairness in machine learning models.
problem Ensuring fairness in machine learning models powered by supervised learning.
method Optimal affine transport and Wasserstein-2 barycenter to characterize the Pareto frontier between prediction error and statistical disparity.
result The proposed method effectively balances prediction accuracy and fairness, as demonstrated by numerical simulations.
ML Compass helps organizations choose AI models that balance utility, cost, and compliance.
problem Selecting AI models that meet user utility, deployment costs, and compliance requirements.
method Develops ML Compass, a framework for constrained optimization over a capability-cost frontier, using internal measures and empirical data.
result ML Compass produces deployment-aware recommendations that differ from capability-only rankings, clarifying trade-offs between capability, cost, and safety.
Understanding optimal prompts for binary sequence predictors is challenging.
problem Finding good prompts for binary sequence predictors is difficult.
method Viewing prompting as finding the best conditioning sequence on a near-optimal sequence predictor, using empirical and statistical analysis.
result Optimal prompts can be better understood given the pretraining distribution, which is not usually available.
Handles verify a manifold conjecture.
problem Verifying a conjecture about submanifolds in manifolds.
method Using handlebodies to construct a family of sets.
result A family of sets forms a neighbourhood basis of the manifold.
ISP improves DNN uncertainty for better subgroup accuracy.
problem Improving accuracy-group robustness in deep neural networks.
method Introspective Self-play (ISP) adds an introspection task to improve bias-awareness and uncertainty.
result ISP improves the accuracy-group robustness trade-off of AL methods.