arXiv research

Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting compact approximations to the best-response function, which maps hyperparameters …

New algorithms achieve decision calibration without sample complexity dependent on feature dimension.

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

Neural operators approximate Stackelberg game solutions.

Improved hypernetwork for efficient neural network hyperparameter tuning.

Best-of-N sampling reveals reward targets from preference data, influencing N and base distribution choices.

Model shows how advisors can manipulate naive investors.

Enhances preference learning by incorporating response times into binary choices.

Two methods for model adaptation compared; fine-tuning outperforms Best-of-N in realizable settings.

New method for sparse kernel selection improves prediction accuracy.

Proposes DeepSDRF for continuous treatment recommendation from clinical survival data.

Paper introduces metrics for evaluating multi-agent policies using best response dynamics.

New RL algorithms find SNE in Markov games with myopic followers.

Paper studies zero-sum games with noisy observations and identifies equilibrium conditions.

ISMCTS-BR learns best responses in large games, approximating worst-case performance.

Best-of-Majority improves inference performance in Pass@$k$ settings.

Deep RL improves Diplomacy performance, outperforming previous methods.

Investors' strategic trading affects asset prices, modeled as a game.

New algorithm improves inference-time alignment without reward hacking.

New method finds all Nash equilibria via vector optimization.

Neural network-based Open-ended conversational agents automatically generate responses based on predictive models learned from a large number of pairs of utterances. The generated responses are typically acceptable as a sentence but are often dull, generic, and certainly devoid of any emotion. In this paper, we present…

In this paper, we propose a convergent parallel best-response algorithm with the exact line search for the nondifferentiable nonconvex sparsity-regularized rank minimization problem. On the one hand, it exhibits a faster convergence than subgradient algorithms and block coordinate descent algorithms. On the other hand,…

Machine learning classifies gravitational wave signals to test General Relativity.

We show that the empirical risk minimization (ERM) problem for neural networks has no solution in general. Given a training set $s_1, \dots, s_n \in \mathbb{R}^p$ with corresponding responses $t_1,\dots,t_n \in \mathbb{R}^q$, fitting a $k$-layer neural network $ν_θ: \mathbb{R}^p \to \mathbb{R}^q$ involves estimation of…

Study of portfolio management under relative performance concerns using mean field games.

We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirec…

Estimation of response functions is an important task in dynamic medical imaging. This task arises for example in dynamic renal scintigraphy, where impulse response or retention functions are estimated, or in functional magnetic resonance imaging where hemodynamic response functions are required. These functions can no…

qEUBO optimizes decision-making with noisy feedback.

New methods for selecting variables in complex biomedical data.

NeuPL learns diverse policies in strategy games efficiently.

We consider learning high-dimensional multi-response linear models with structured parameters. By exploiting the noise correlations among responses, we propose an alternating estimation (AltEst) procedure to estimate the model parameters based on the generalized Dantzig selector. Under suitable sample size and resampli…

The paper provides risk bounds for learning many response functions using linear regression.

New algorithms achieve logarithmic regret in KL-regularized Markov games.

We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. …

Flexible models predict US Census survey response rates.

New method optimizes language model performance for test-time strategies.

Study analyzes price response and spread impact in foreign exchange markets.

Algorithm solves online binary classification and infinite games using ERM oracle.

Holistic GLMs add constraints for better model quality.

When simulating a complex stochastic system, the behavior of output response depends on input parameters estimated from finite real-world data, and the finiteness of data brings input uncertainty into the system. The quantification of the impact of input uncertainty on output response has been extensively studied. Most…

Quantile regression with ReLU networks achieves minimax rates for various function types.

Estimates personalized treatment response curves using covariates.

A simplified model for brain activity measurement.

Study analyzes non-Markovian effects in financial markets over multiple years.

New algorithm for solving minimax problems over distributions converges to Nash equilibrium.

Digital personas improve survey results for stable attributes but fail for subjective responses.

Bayesian model ranks treatments in multi-response experiments.

Identity-link IRT improves TVD-MI scores without curvature violations.