Quantum machine learning offers advantages for broader learning tasks.
problem Demonstrate QML advantage over classical methods for general learning tasks.
method Construct a new family of supervised learning tasks and prove their hardness.
result Prove provable advantage of QML based on general quantum computational advantages.
This paper improves Q-learning bounds using reference-advantage decomposition.
problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.
Machine learning predicts quantum advantage in noisy quantum walks.
problem Finding optimal graph types and coherence requirements for quantum advantage.
method Convolutional neural network trained on simulated examples of quantum walks on cycle graphs.
result Machine learning can predict quantum advantage for a wide range of decoherence parameters.
DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.
problem Pathologies in standard policy gradients, leading to poor updates and over-allocation of gradient budget.
method Introduces Delightful Policy Gradient (DG) that gates each term with a sigmoid of advantage and surprisal.
result DG provably improves directional accuracy in a single context and shifts the expected gradient closer to the oracle across multiple contexts.
UCB-Advantage learns MDPs with O ( H 2 S A T ) O(\sqrt{H^2SAT}) O ( H 2 S A T ) regret.
problem Model-free reinforcement learning in finite-horizon MDPs.
method Reference-Advantage decomposition for low regret.
result Achieves i l d e O ( H 2 S A T ) ilde{O}(\sqrt{H^2SAT}) i l d e O ( H 2 S A T ) regret, matching best known bounds. New method learns time-varying home field advantage in football.
problem Discovering causal factors behind home field advantage in sports.
method DYNAMO: a novel causal discovery method for non-stationary processes.
result Time-varying home field advantages influenced by referee bias.
Study compares adaptive vs fixed query learning methods.
problem Comparing adaptive and fixed query learning methods for task approximation.
method Examined in-context and agentic learning in two settings: unrestricted and realizable.
result Adaptivity does not hinder performance in unrestricted setting but can in realizable setting.
This paper re-examines conformal e-prediction and its advantages over conformal prediction.
problem The relationship between conformal prediction and conformal e-prediction.
method Systematic re-examination of conformal prediction and conformal e-prediction from a modern perspective.
result Conformal e-prediction has advantages such as ease of designing conditional predictors and guaranteed validity of cross-predictors.
Study on when RLVR can learn compositional problems.
problem Understanding when RLVR can learn compositional problems.
method Theoretical analysis of task-advantage ratio to characterize learnability.
result Identified conditions for learnability of compositional problems.
Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.
problem Quantum advantage in pricing derivatives.
method Re-parameterization method combining pre-trained variational circuits and fault-tolerant quantum computing.
result Benchmark use cases require 8k logical qubits and a T-depth of 54 million.
Gradient descent benefits from tangent kernel advantages under specific conditions.
problem Comparing gradient descent with tangent kernel methods in learning.
method Analysis of gradient descent and tangent kernel methods under different conditions.
result Gradient descent can achieve small error only if tangent kernel methods have a non-trivial advantage, but this advantage can be very small.
We develop Riemannian Stein Variational Gradient Descent (RSVGD), a Bayesian inference method that generalizes Stein Variational Gradient Descent (SVGD) to Riemann manifold. The benefits are two-folds: (i) for inference tasks in Euclidean spaces, RSVGD has the advantage over SVGD of utilizing information geometry, and …
Two new criteria help understand the advantage of deep neural networks.
problem Understanding the advantage of deepening neural networks.
method Proposed two new criteria to evaluate the expressivity of functions computable by deep neural networks.
result Increasing layers is more effective than increasing units in improving the expressivity of deep neural networks.
Quantum algorithms accelerate financial risk computation.
problem Accelerating the computation of financial market risk.
method Quantum gradient estimation algorithms for market sensitivities.
result Significant reduction in resource requirements for financial quantum advantage.
Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…
The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.
problem Scalarization issues in A2C RL algorithms leading to gradient overlap and uncontrolled noise.
method Proposes techniques to avoid gradient overlap and noise in A2C RL algorithms.
result Pilot experiments show the proposed method speeds up training in A2C RL algorithms.
New proof shows local wealth condensation in economic models with biases.
problem Economic models with biases leading to wealth condensation.
method Elementary proof based on properties of wealth distributions.
result Local wealth condensation observed in models with wealth or poverty advantages.
DG separates successes and failures by gating updates with advantage and surprisal.
problem Negative learning from surprising data in distributed reinforcement learning.
method DG gates each update with the product of advantage and surprisal, suppressing failures and preserving successes.
result DG outperforms other methods in various challenging reinforcement learning tasks.
Quantum Boltzmann Machines trained on quantum annealers produce noisy synthetic data.
problem Training quantum Boltzmann machines on quantum annealers for financial data generation.
method Used D-Wave Advantage 4.1 quantum annealer to train QBMs and compare with classical RBMs.
result Quantum Boltzmann Machines trained on quantum annealers are noisier and less effective than classical RBMs.
Improved SAC with AWMP for better control tasks.
problem Discontinuous and non-smooth optimal policies in reinforcement learning.
method Advantage Weighted Mixture Policy (AWMP) for SAC, learning state-specific weights.
result SAC with AWMP outperforms SAC in four control tasks.
This study improves quantum classifiers by optimizing data preprocessing.
problem Quantum Machine Learning advantages are not yet clearly demonstrated.
method Used Linear Discriminant Analysis (LDA) for data preprocessing.
result Variational Quantum Algorithm (VQA) outperforms classical classifiers.
Quantum circuits reveal pathways to dequantization in machine learning models.
problem Navigating the complex landscape of quantum machine learning models and algorithms.
method Introducing a framework connecting quantum circuit structure to function representability.
result Fundamental properties of quantum circuits determine classical simulability of models.
VQAs use classical optimization to train quantum circuits, promising quantum advantage.
problem High computational cost of quantum simulations and solving large-scale problems.
method Variational Quantum Algorithms (VQAs) use classical optimizers to train parametrized quantum circuits.
result VQAs are a promising strategy for obtaining quantum advantage.
Convolutional networks outperform fully-connected ones in certain tasks.
problem Understanding the computational advantage of convolutional networks over fully-connected networks.
method Demonstrated a computational advantage through a specific problem class.
result Convolutional networks can solve certain problems that fully-connected networks cannot, even with gradient descent.
Quantum algorithms improve VaR and CVaR estimation for financial derivatives.
problem Quantum advantage in financial risk analysis of derivatives.
method Two quantum algorithms: QSP and QSP-based approach.
result QSP-based approach requires fewer quantum resources for the same accuracy.
Quantum computing offers energy savings over classical computing.
problem Energy efficiency in computing services.
method Cournot competition model constrained by energy usage.
result Quantum computing firms can outperform classical counterparts in energy efficiency.
Quantum walks are at the heart of modern quantum technologies. They allow to deal with quantum transport phenomena and are an advanced tool for constructing novel quantum algorithms. Quantum walks on graphs are fundamentally different from classical random walks analogs, in particular, they walk faster than classical o…
Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
problem Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
method Formal study of PAC learnability of MLP layers with activation sparsity.
result Classes of functions with activation sparsity lead to provable computational and statistical advantages over their non-sparse counterparts.
Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…
Bayesian estimators for causal inference using hierarchical Gaussian Processes.
problem Estimating causal effects in sharp and fuzzy RD/RK designs.
method Hierarchical Gaussian Process models for regression and classification.
result Hierarchical GP models improve precision and coverage of RD/RK estimations.
Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.
problem Near-optimal federated Q-learning with low communication cost.
method Reference-advantage decomposition for variance reduction, synchronization between agents and server, policy update.
result Achieves almost optimal regret and near-linear regret speedup compared to single-agent learning.
Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.
problem Balancing exploration and exploitation in reinforcement learning.
method Soft policy optimization with entropy and dual-track advantage estimator (DTAE).
result DTAE accelerates RL algorithm convergence and improves performance.
DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.
problem DRL agents struggle at high decision frequencies, leading to poor performance.
method Proved that DRL agents' action-conditioned return distributions collapse to their policy's return distribution as decision frequency increases. Defined superiority as a probabilistic generalization of advantage for high-frequency value-based RL.
result Proper modeling of superiority distribution improves performance of controllers at high decision frequencies.
Modified BFGS and LBFGS++ libraries boost performance for non-parallelizable functions.
problem Improving performance of non-parallelizable functions using SIMD and AAD.
method Modifications to BFGS and LBFGS++ libraries, utilizing SIMD and Automatic Differentiation (AAD).
result Up to 3.8 times faster for European Swaption curve calibration and 1.4 times faster for LMM model calibration.
Quantum networks offer exponential communication savings for large machine learning models.
problem Training and inference of large models require efficient communication.
method Quantum encoding and gradient descent for distributed computation.
result Exponential reduction in communication for gradient descent on quantum networks.
Hybrid quantum-classical RL model solves standard benchmark tasks and proves quantum advantage.
problem Challenges in reinforcement learning, especially in solving standard benchmarking tasks.
method Parametrized quantum circuits in a hybrid quantum-classical RL model.
result Demonstrates quantum advantage in solving standard benchmarking tasks and intractable classical problems.
Quantum kernels show no advantage in stock return prediction, but differ in stability metrics.
problem Determining if quantum kernels improve stock return prediction.
method Controlled horse race on Chinese A-share market with identical training subsamples and tuning budgets.
result Quantum kernels do not outperform classical RBF controls in cross-sectional stock return prediction.
With the abundance of data in recent years, interesting challenges are posed in the area of recommender systems. Producing high quality recommendations with scalability and performance is the need of the hour. Singular Value Decomposition(SVD) based recommendation algorithms have been leveraged to produce better result…
Distributed securities exchanges may become de facto fragmented if they span geographical regions with asymmetric computer infrastructure. First, we build an economic model of a decentralized exchange with two miner clusters, standing in for compact areas of economic activity (e.g., cities). "Local" miners in the area …
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…
In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods. However, not all domains of machine learning have benefited equally from quantum enhancements. Notably, deep learning and rein…
Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.
problem Performance saturation in RL algorithms for LLMs.
method Entrocraft uses rejection sampling to bias advantage distributions for customized entropy schedules.
result Entrocraft significantly improves generalization, output diversity, and long-term training in 4B models.
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…
The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or agains…
Enhances time-series modeling by dropping patches, improving efficiency and adaptability.
problem Improving masked time-series modeling efficiency and adaptability.
method DropPatch method, which randomly drops sub-sequence level patches.
result DropPatch improves pre-training efficiency and adaptability in various learning scenarios.
MB-DQN uses different backup lengths for improved reinforcement learning.
problem Improving reinforcement learning with multi-step returns.
method Integrates multi-step returns into bootstrapped DQN with different backup lengths.
result MB-DQN maintains advantages of different backup lengths.
Investors suffer welfare loss despite having better information.
problem Welfare loss among investors with absolute information advantages.
method Examined financial markets with heterogenous investors and objective measures of welfare.
result Investors incur welfare loss even with better information, revealing a double loss phenomenon.
Quantum correlations enhance generative models, providing a new resource for machine learning.
problem Capturing complex probability distributions in unsupervised learning.
method Theoretical and numerical analysis of quantum correlations in generative models.
result Quantum nonlocality and contextuality provide an expressivity advantage over classical models.