Novelty search learns attentional layers to quickly explore and guess numbers.
problem Exploring and guessing numbers quickly in structured spaces.
method Attentional neural network layers trained on supervised learning of local sensory-motor contingencies.
result Greedy local policies can quickly explore structured spaces and guess numbers.
The paper analyzes how good initial guesses affect the amount of data needed for low-rank matrix recovery.
problem Theoretical guarantee of local optimization algorithms requires excessive data to prevent spurious local minima.
method Quantifies the relationship between initial guess quality and sample complexity using restricted isometry constant.
result A linear improvement in initial guess quality leads to a constant factor improvement in sample complexity.
Randomly guessing weights helps analyze RL benchmarks objectively.
problem Understanding the complexity of reinforcement learning benchmarks.
method Generate policy networks by randomly guessing their parameters, evaluate on benchmarks, and analyze results.
result Small untrained networks can provide a robust baseline for various RL tasks.
GUESS improves surrogate model accuracy with adaptive sampling.
problem Creating accurate surrogate models with limited data.
method Gradient and Uncertainty Enhanced Sequential Sampling (GUESS) using predictive uncertainty and Taylor expansion.
result GUESS achieved highest sample efficiency compared to other strategies.
PassGAN uses GANs to autonomously generate passwords from real leaks, outperforming traditional methods.
problem Generating passwords efficiently and accurately using machine learning.
method PassGAN employs a Generative Adversarial Network (GAN) to learn password distributions from real leaks.
result PassGAN outperforms traditional password guessing tools, especially in generating a large number of high-quality guesses.
A new algorithm finds minimizers in dueling optimization with a monotone adversary.
problem Finding minimizers in dueling optimization with a monotone adversary.
method Introduces and studies dueling optimization with a monotone adversary, designs an efficient randomized algorithm.
result Efficient algorithm incurs cost O ( d ) O(d) O ( d ) and iteration complexity O ( d log ( 1 / ε ) 2 ) O(d\log(1/\varepsilon)^2) O ( d log ( 1/ ε ) 2 ) , asymptotically optimal. Counterfactual data augmentations may not ensure OOD robustness if performed by a context-guessing machine.
problem Deep learning models lack out-of-distribution robustness due to reliance on spurious features.
method Theoretical analysis and demonstration of counterfactual data augmentations performed by a context-guessing machine.
result Counterfactual data augmentations by a context-guessing machine do not lead to robust OOD classifiers.
Forward gradients improve neural network training without backpropagation issues.
problem Training neural networks without backpropagation's locking and memorization problems.
method Using directional derivatives in forward differentiation mode, with biased guesses based on feedback from small auxiliary networks.
result Using gradients from a local loss as a candidate direction improves Forward Gradient methods.
The paper introduces negative controls to evaluate causal discovery algorithms, improving their reliability.
problem Lack of a general guideline for evaluating causal discovery algorithms.
method Derive exact distributional results under random guessing for evaluation metrics and propose a pipeline for using negative controls.
result Evaluation metrics can achieve very favorable values under random guessing, highlighting the need for negative control results.
Improved Anderson acceleration speeds up nonlinear optimization.
problem Optimizing nonlinear functions efficiently.
method Combining Anderson acceleration with Chebyshev polynomials.
result Achieves optimal convergence rate for nonlinear problems.
This paper analyzes data-driven Newsvendor problems and finds a wide range of possible regrets.
problem Guessing the number drawn from an unknown distribution with asymmetric costs.
method Unified analysis using the notion of clustered distributions and new lower bounds.
result The entire spectrum of achievable regrets from 1 / n 1/\sqrt{n} 1/ n to 1 / n 1/n 1/ n is possible. Novel proof of Shepp's theorem using martingales.
problem Determining the optimal time to sell a bond.
method Guessing and proving the optimal control function with martingales.
result Proved Shepp's theorem using a novel approach.
Untrained neural networks can unfairly assign predictions to the same class.
problem Biasing effects in neural networks during initial training phases.
method Theoretical analysis of deep neural networks, focusing on Initial Guessing Bias (IGB).
result Model structure and preprocessing methods influence IGB.
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box stochastic simulator for both the problem domain and the agent. We relate classic policy gradient techniques to recently introduced black-box…
Unhinged loss minimization fails to improve classifier accuracy for simple data.
problem Accuracy of classifiers minimizing the unhinged loss.
method Minimizing the unhinged loss function.
result Minimizing the unhinged loss yields classifiers with accuracy no better than random guessing for simple data.
Machine-generated interpretations do not improve users' guessing accuracy in image classifiers.
problem Determining the usefulness of machine-generated explanations for deep neural networks.
method Human evaluation of crowd workers guessing incorrectly predicted labels with and without visual interpretations.
result Showing machine-generated visual interpretations decreased average guessing accuracy by about 10%.
Study finds users mostly use recent market and decision information to guess market direction.
problem Limited ability to model and predict human decision-making in stock markets.
method Used networks inference with stochastic block models (SBM) to find most predictive model of unobserved decisions.
result Users mostly use recent information to guess market direction, and their decision-making strategies are analogous to behaviors in other contexts.
A method to derive Lagrangians from field equations in metric-affine theories of gravity.
problem Deriving Lagrangians from field equations in metric-affine theories of gravity.
method Variational completion method to transform field equations into Euler-Lagrange equations and find a Lagrangian.
result Starting from metric equations, full metric equations and Lagrangian can be derived up to metric-independent terms.
MESSY estimation recovers symbolic density functions from samples using maximum entropy.
problem Estimating probability density functions from limited samples.
method Maximum-Entropy approach with gradient flow and symbolic regression.
result Efficiently finds optimal symbolic expressions for unknown distributions.
We study a variation of the minority game. There are N agents. Each has to choose between one of two alternatives everyday, and there is reward to each member of the smaller group. The agents cannot communicate with each other, but try to guess the choice others will make, based only the past history of number of peopl…
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.
Novel neural network models using convex optimization for improved training.
problem Improving the training of neural networks.
method Representing activation functions as argmin of convex optimization problems, applying block-coordinate descent methods.
result Proposed models provide excellent initial guesses and avenues for extensions.
The abstract discusses scalar curvature and its implications.
problem Implications of lower scalar curvature bounds on manifolds.
method Analyzes existing conjectures and questions.
result No new results are presented, just a collection of open problems.
Adapting physics methods to data science for efficient feature learning.
problem Learning relevant features from large datasets efficiently.
method Layered tree tensor networks that scale linearly with data dimensions and training set size. Uses unsupervised learning for most layers and supervised learning for the top layer.
result Supervised classification of MNIST and fashion-MNIST datasets with good performance using fewer features.
We obtain the classical Hanner inequalities by the Bellman function method. These inequalities give sharp estimates for the moduli of convexity of Lebesgue spaces. Easy ideas from differential geometry help us to find the Bellman function using neither "magic guesses" nor calculations.
Study reduces human labeling in LLM-based classification systems.
problem Minimizing human intervention in training LLM-based classification systems.
method Active learning framework with Conservative Hull-based Classifier (CHC), Center-based Classifier (CC), and Generalized Hull-based Classifier (GHC).
result CHC achieves O ( log d T ) \mathcal{O}(\log^d T) O ( log d T ) regret and is minimax optimal for d = 1 d=1 d = 1 . GHC bridges the gap between different regimes. New methods improve accuracy in detecting concentric objects.
problem Detecting concentric geometric objects in noisy data.
method Developed new estimators and compared performance of existing methods.
result New methods outperform existing non-iterative methods and are robust to noise.
Study on Finsler spaces with unique prime geodesics.
problem Estimating the number of orbits of prime closed geodesics in Finsler manifolds.
method Generalizing works on two prime closed geodesics to equivariant situation, studying homogeneous Finsler geometry.
result Closed Finsler manifold with only one orbit of prime closed geodesic is a compact rank-one Riemannian symmetric space when dimension is even or metric is reversible.
New algorithm estimates mean in high dimensions with nearly-linear time, robust to corrupted data.
problem Estimating mean in high-dimensional data with adversarial corruption.
method Near-linear time algorithms using SDPs parameterized by current guess of mean.
result Approximates true mean within optimal error guarantees, independent of initial guess.
Top-k multiclass SVM optimizes for top-k error in ambiguous image classification.
problem Ambiguity in large-class image classification problems.
method Proposes a generalization of multiclass SVM to optimize for top-k error using a tight convex upper bound and efficient projection onto the top-k simplex.
result Consistent improvements in top-k accuracy compared to baselines on five datasets.
SVD improves neural network optimization.
problem Optimizing neural networks.
method Using SVD as an initial guess for neural network parameters.
result Better optimization results.
Paper introduces methods for more reliable probabilistic predictions with confidence intervals.
problem Inaccurate labeling of datasets due to unreliable probabilistic predictions from weak labeling functions.
method Proposes a methodology to provide confidence intervals for label probabilities using uncertainty sets of distributions.
result Improves reliability of probabilistic predictions and provides confidence intervals for label probabilities.
We consider the fundamental problem of solving quadratic systems of equations in n n n variables, where y i = ∣ ⟨ a i , x ⟩ ∣ 2 y_i = |\langle \boldsymbol{a}_i, \boldsymbol{x} \rangle|^2 y i = ∣ ⟨ a i , x ⟩ ∣ 2 , i = 1 , … , m i = 1, \ldots, m i = 1 , … , m and x ∈ R n \boldsymbol{x} \in \mathbb{R}^n x ∈ R n is unknown. We propose a novel method, which starting with an initial guess computed by means of a …
A spin network is a cubic ribbon graph labeled by representations of S U ( 2 ) \mathrm{SU}(2) SU ( 2 ) . Spin networks are important in various areas of Mathematics (3-dimensional Quantum Topology), Physics (Angular Momentum, Classical and Quantum Gravity) and Chemistry (Atomic Spectroscopy). The evaluation of a spin network is an integ…
New tool improves scalability of data-driven invariant inference.
problem Scaling data-driven invariant inference to programs with many variables.
method Developed oasis tool to improve scalability.
result Outperforms state-of-the-art systems on benchmarks.
New model shows weak teachers can help strong students learn even with imperfect labels.
problem Improving strong student's performance with weak teacher's imperfect pseudolabels.
method Stylized overparameterized spiked covariance model with Gaussian covariates, proving two phases of generalization.
result Provable successful and random guessing phases of strong student's generalization.
PINNs solve neuronal parameter and state estimation problems with limited data.
problem Estimating parameters and hidden state variables from noisy partial data in multiscale neuronal models.
method Physics-informed neural networks (PINNs) for joint state and parameter estimation.
result PINNs deliver robust and accurate parameter inference and state reconstruction, even with limited data.
Study robust learning of Lipschitz functions under corrupted binary signals.
problem Learning a Lipschitz function with corrupted binary signals in a context of unknown corruption rounds.
method Introduced agnostic checking and new analysis techniques to design algorithms for symmetric and pricing losses.
result Achieved small cumulative loss for both symmetric and pricing losses.
New study shows neural networks can generalize without gradient descent, especially in deep settings.
problem Whether neural networks need gradient descent for generalization.
method Theoretical study of matrix factorization with linear and non-linear activation, comparing gradient descent to Guess & Check.
result Generalization under Guess & Check deteriorates with increasing width but improves with depth, challenging conventional wisdom.
Improved efficient robust regression with near-linear time and subquadratic samples.
problem Robust linear regression with unknown covariance matrix under Gaussian covariates.
method Near-linear time algorithm using subquadratic samples, complemented by SQ and polynomial lower bounds.
result Achieves prediction error O ( ε κ ) O(\sqrt{εκ}) O ( ε κ ) for ε κ ≲ 1 εκ\lesssim 1 ε κ ≲ 1 , improving over prior works. Improves generative Visual Dialog by asking diverse questions.
problem Generative Visual Dialog models degrade after a few rounds of interaction.
method Introduce a simple auxiliary objective to incentivize Qbot to ask diverse questions.
result Better dialog diversity, consistency, fluency, and detail with improved image relevance.
Paper introduces a new loss function for deep imbalanced classification.
problem Class ambiguity and imbalance in large datasets.
method Stochastic top-K hinge loss based on smoothed top-K operator.
result Our loss function significantly outperforms other baseline loss functions in imbalanced datasets.
EM algorithm estimates coefficients of a mixture of two linear regressions.
problem Estimating coefficients of a mixture of two linear regressions.
method Expectation Maximization (EM) algorithm with convergence guarantees.
result Empirical EM iterates converge to the target parameter vector at the parametric rate.
New method detects if data points were used in training models with low cost and high power.
problem Detecting if a particular data point was used in training a model.
method Fine-grained modeling of null hypothesis in likelihood ratio tests, leveraging reference models and population data.
result RMIA has superior test power compared to prior methods, even at extremely low false positive rates.
Study tackles inverse problems on low-dimensional manifolds, proving stability and proposing a reconstruction algorithm.
problem Inverse problems in infinite-dimensional spaces with nonlinear and ill-posed nature.
method Assumption of low-dimensional manifold, proving stability, proposing Landweber-type algorithm.
result Global convergence of the proposed algorithm, Lipschitz stability for specific inverse problems.
A new deep learning framework improves multi-label classification performance.
problem Extracting hidden correlations between labels in multi-label classification.
method Proposes a novel deep learning framework with a memory structure to rethink label correlations.
result Improves multi-label classification performance across different evaluation criteria.
The paper predicts Bitcoin volatility using order flow images.
problem Predicting short-term volatility of Bitcoin prices.
method Transformed order flow data into images, trained CNN and ResNet models.
result Order flow representation with CNN achieves best performance, with RMSPE of 0.85+/-1.1.
Solves utility maximization for delayed informed investors.
problem Maximizing utility in a discrete time framework with delayed information.
method Utilizes theory from [4] and optimal portfolio guessing.
result Solution for exponential utility maximization in a multivariate normal setting with delay.