Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

242485727969 · Jun 202019922001200920172026
48 results for Optimization benchmarks

YAHPO Gym introduces a new benchmark for evaluating hyperparameter optimization methods.

problem Evaluating and comparing hyperparameter optimization methods on well-curated benchmark suites.
method Surrogate-based benchmark collection of 14 scenarios, each with multi-fidelity and multi-objective hyperparameter optimization problems.
result Surrogate-based benchmarks produce more faithful results than tabular benchmarks.

Proposes a new framework for optimizing utility with state-dependent benchmarks.

problem Various interpretations of benchmarks in utility functions.
method General framework of state-dependent utility optimization with stochastic benchmarks.
result Provides optimal solutions and addresses issues of well-definedness and feasibility.

Study optimizes portfolio to minimize relative drawdown duration, penalizing unfavorable performance states.

problem Minimizing relative drawdown duration in portfolio optimization relative to a benchmark.
method Introduces a benchmark-relative drawdown-duration criterion penalizing unfavorable performance states. Uses a one-dimensional Markovian representation and Hamilton-Jacobi-Bellman equation.
result Derives explicit projection-based characterization of the optimal feedback control and identifies geometric settings for unique strong solutions.

Study benchmarks TSC algorithms in distinguishing diffusions using the likelihood ratio test.

problem Benchmarking optimality of TSC algorithms in distinguishing diffusion processes.
method Proposes to benchmark TSC algorithms using the likelihood ratio test (LRT).
result LRT benchmarks are computationally efficient and can be applied to various time series types.

Olympus benchmarks optimization algorithms for noisy experiments.

problem Benchmarking optimization algorithms on realistic experimental scenarios is challenging.
method Introduces Olympus, a software package for benchmarking optimization algorithms on synthetic experiments.
result Mitigates barriers in benchmarking optimization algorithms on realistic experimental scenarios.

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon protocol for the quantitative and reproducible evaluation of optimization strategies…

2019-03-13abs ↗pdf ↗

Optimal asset allocation strategy outperforms stochastic benchmark.

problem Achieving higher terminal wealth than a stochastic benchmark.
method Data-driven Neural Network optimization framework for dynamic asset allocation.
result Optimal adaptive strategy outperforms benchmark with higher median and right-skewed terminal wealth.

This work introduces benchmarks for evaluating nanophotonic structures in design simulations.

problem Design and understanding of nanophotonic structures for various applications.
method Development of frameworks and benchmarks for evaluating nanophotonic structures in parametric design problems.
result Strategic use of evaluation fidelity in enhancing structure designs.

New benchmark protocol evaluates neural network optimizers for efficiency and data shift sensitivity.

problem Benchmarking neural network optimizers with hyperparameter complexity and data shift sensitivity.
method Proposed a new evaluation protocol combining end-to-end and data-addition training efficiency, using bandit hyperparameter tuning and human study validation.
result No clear winner across all tasks, highlighting the complexity of optimizer performance.

Combines absolute and relative wealth in portfolio optimization with power utility functions.

problem Optimizing portfolios with both absolute and relative wealth considerations.
method Integrates power utility functions for absolute and relative wealth, considering multiple benchmarks.
result Obtains an explicit solution for portfolio optimization combining absolute and relative wealth.

Survey and benchmark high-dimensional Bayesian optimization of discrete sequences.

problem Heterogeneous experimental set-ups and technical barriers in high-dimensional Bayesian optimization of discrete sequences.
method Unified framework and software libraries to test and benchmark methods.
result Unified framework and software libraries for testing and benchmarking high-dimensional Bayesian optimization methods.

Investors optimize their portfolios within a Wasserstein ball to match a benchmark's risk profile.

problem Optimizing portfolio performance while maintaining risk proximity to a benchmark.
method Optimal dynamic strategy selection based on minimizing distortion risk measures within a Wasserstein ball.
result An optimal dynamic strategy exists and can be calculated through isotonic projections.

Study optimal consumption with relaxed benchmarks and drawdown constraints.

problem Optimal consumption under relaxed benchmark tracking and consumption drawdown constraint.
method Transformed stochastic control problem into regular control problem with state-control constraints, then solved using dual transform and optimal consumption behavior.
result Closed-form solution for optimal investment and consumption in feedback form.

MLPerf, an emerging machine learning benchmark suite strives to cover a broad range of applications of machine learning. We present a study on its characteristics and how the MLPerf benchmarks differ from some of the previous deep learning benchmarks like DAWNBench and DeepBench. We find that application benchmarks suc…

2019-08-24abs ↗pdf ↗

Benchopt automates machine learning benchmarking across languages and hardware.

problem Limited transparency and tedious re-implementation work in machine learning validation.
method A collaborative framework for automating, reproducing, and publishing optimization benchmarks.
result Demonstrates practical findings that highlight the importance of details in machine learning validation.

This study benchmarks fifteen deep learning optimizers and identifies a subset that generally performs well.

problem Choosing the best optimizer in deep learning is challenging and often based on anecdotes.
method An extensive, standardized benchmark of fifteen popular optimizers, analyzing over 50,000 runs.
result A subset of optimizers and parameter choices generally leads to competitive results.

The paper solves a control problem using reflections to track a benchmark process.

problem Optimal consumption with a benchmark process that grows over time.
method Introduced two auxiliary state processes with reflections to transform the problem into a more tractable form.
result Established the existence of a unique classical solution to the dual PDE.

Optimal portfolio tracking with dynamic capital injection into a ratcheting benchmark.

problem Optimizing a portfolio's performance by dynamically adding capital to a non-decreasing benchmark.
method Formulated as an unconstrained control problem with a running maximum cost, transformed into an auxiliary problem with a nonlinear HJB equation, solved using probabilistic representation and stochastic flow analysis.
result Established the existence of a unique classical solution to the HJB equation, providing feedback optimal portfolio strategies.

The paper introduces a new divergence for portfolio management to outperform a benchmark.

problem Maximizing expected utility of outperformance over a benchmark with constraints.
method Uses αα-Bregman-Wasserstein divergence to penalize underperformance more than overperformance.
result Proves existence and uniqueness of optimal portfolio strategy and conditions for constraints binding.

Automated HPO design using Bayesian optimization and benchmarking.

problem Designing effective hyperparameter optimization algorithms is manual and lacks systematic understanding.
method Formalized space of HPO candidates, Bayesian optimization for search, ablation analysis.
result Simple configurations can perform well in HPO, especially with right parameters.

This study benchmarks AI agents for personalized retail promotions using simulations.

problem Optimizing coupon targeting for sparse customer purchase events.
method Comprehensive simulations of customer shopping behaviors; training RL agents on batch data.
result Contextual bandit and deep RL methods outperform static policies in sparse reward environments.

Study proposes a neural network approach for high inflation investment portfolios with leverage constraints.

problem Optimizing investment portfolios with high inflation and bounded leverage constraints.
method Formulated an optimal control problem, established a closed-form solution, and developed a novel LFNN approach.
result The LFNN strategy outperforms a passive benchmark by about 200 bps with a high probability of success.

Investigate using LETFs to outperform benchmarks, finding them more likely to succeed.

problem The controversy and popularity of LETFs in constructing portfolios.
method Systematic investigation using IR-optimal strategies with LETFs and VETFs, including neural network-based approaches.
result IR-optimal strategies with LETFs outperform benchmarks and achieve partial stochastic dominance.

The paper extends Merton's problem by adding benchmark tracking, finding optimal strategies.

problem Maximizing consumption utility with a trade-off against benchmark performance.
method Developed a convex duality theorem and derived optimal strategies for specific cases.
result Found optimal portfolio and consumption strategies for CRRA utility and geometric Brownian motion benchmarks.

Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges absent from other domains: optimizations that improve training throughput can incre…

2019-10-02abs ↗pdf ↗

Optimistic Mirror Descent framework improves bidding strategies in non-stationary first-price auctions.

problem Optimizing bidding strategies in non-stationary first-price auctions.
method Introducing Optimistic Mirror Descent (OMD) framework with novel optimism configuration.
result Minimax-optimal dynamic regret rates achieved for non-stationary first-price auctions.