Study finds some datasets benefit from small training samples.
problem The effectiveness of large training datasets in modern computer vision.
method Gradient-based importance measure to analyze training images.
result Some datasets can be trained with smaller samples, others not.
In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size. In previous studies, researchers conducted random sampling which is according to the input data but independent on the response variable, however the response variab…
GIT uses gradient estimators to target interventions for causal discovery.
problem Challenges in inferring causal structure from observational data.
method GIT uses gradient estimators to target interventions for causal discovery.
result GIT performs on par with competitive baselines, surpassing them in low-data regimes.
In recent years, Deep Learning has become the go-to solution for a broad range of applications, often outperforming state-of-the-art. However, it is important, for both theoreticians and practitioners, to gain a deeper understanding of the difficulties and limitations associated with common approaches and algorithms. W…
MACQ method explains deep learning models by analyzing feature contributions across prediction levels.
problem Explaining deep learning model predictions.
method Global gradient-based, model-agnostic approach focusing on marginal attribution.
result MACQ separates feature contributions from interaction effects and visualizes 3-way relationships.
A new method MixGDA combines mixup and gradient-based data augmentation for SSL.
problem Improving semi-supervised learning performance with limited labeled data.
method Gradient-based Data Augmentation (GDA) combined with mixup methods.
result MixGDA achieves state-of-the-art performance in various SSL benchmarks.
A new deep learning model for tabular data improves accuracy over GBDT.
problem Improving accuracy in tabular data classification.
method Differentiable forest with sparse attention mechanism.
result The differentiable forest achieves higher accuracy than GBDT on tabular datasets.
NeuralSort optimizes sorting networks using continuous relaxations.
problem Non-differentiability of sorting operator hinders gradient-based optimization.
method Continuous relaxation of sorting operator to unimodal row-stochastic matrices, enabling gradient-based optimization.
result Gradient-based stochastic optimization over permutations is achieved.
This work explores the relation between depth and expressivity in neural networks.
problem Understanding the power of depth in neural networks and its relation to gradient-based optimization.
method Depth separation argument for distributions with fractal structure, proving that deep networks can express fine details efficiently but shallow ones cannot.
result The success of learning deep networks depends on whether the distribution can be well approximated by shallower networks.
Neural networks can learn Boolean circuits with local correlation.
problem Learning Boolean circuits with neural networks is computationally hard.
method Observing local correlation between input patterns and target labels, focusing on tree-structured Boolean circuits.
result Local correlation determines the success or failure of optimization in learning Boolean circuits.
New method preserves convergence rates in gradient-based optimization.
problem How to discretize gradient-based optimization systems while preserving stability and convergence rates.
method Geometric framework for dissipative symplectic integration.
result Dissipative symplectic integrators preserve rates of convergence up to a controlled error.
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differen…
A new method for efficient inference in probabilistic programs with mixed support.
problem Challenges in inference for programs with both continuous and discrete latent variables.
method Stochastic gradient Markov Chain Monte Carlo algorithms.
result Outperforms existing composing inference baselines and works almost as well as inference in marginalized versions.
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with non…
Bayesian inference plays an important role in advancing machine learning, but faces computational challenges when applied to complex models such as deep neural networks. Variational inference circumvents these challenges by formulating Bayesian inference as an optimization problem and solving it using gradient-based op…
This paper bounds the Lipschitz constants of neural networks and their gradients.
problem Estimating the Lipschitz constant of complex models like neural networks.
method Local upper and lower bounds on Lipschitz constants computed with respect to network parameters.
result It is impossible to derive global upper bounds for the Lipschitz constants of neural networks.
Meta learning improves with contextualizers that adapt to examples.
problem Few shot classification with limited labeled data.
method Implement contextualizers as generalizable prototypes for gradient-based meta learning.
result Contextualizers significantly boost performance on various few shot learning datasets.
QEM uses parallel importance weighting for fast approximate Bayesian inference.
problem Bayesian inference challenges in large models with many observations and latent variables.
method Expectation Maximization (EM) with massively parallel importance weighting.
result QEM is faster and more scalable than RWS and VI.
Proposes a differentiable hypergeometric distribution for learning group importance.
problem Learning the sizes of subsets in applications like clustering and weakly-supervised learning.
method Introduces a reparameterizable hypergeometric distribution to model group sizes and learn their relative importance.
result Outperforms previous methods in weakly-supervised learning and clustering.
DAIS improves AIS for differentiable marginal likelihood estimation.
problem Differentiable marginal likelihood estimation for complex models.
method Proposes Differentiable Annealed Importance Sampling (DAIS) to make AIS differentiable.
result DAIS achieves convergence and consistency in Bayesian linear regression.
Gradient-based algorithm improves model performance with triage.
problem Improving model accuracy with human expert involvement.
method Formal characterization of triage, optimal triage policy as deterministic threshold rule, gradient-based algorithm.
result Gradient-based algorithm finds triage policies and models with increasing performance.
Method generates visual explanations for similarity models without classification.
problem Lack of visual explanations for similarity models trained without classification loss.
method Gradient-based visual attention using learned feature embeddings.
result Attention maps improve model performance and can be used as constraints.
Quantum circuit Born machines are generative models which represent the probability distribution of classical dataset as quantum pure states. Computational complexity considerations of the quantum sampling problem suggest that the quantum circuits exhibit stronger expressibility compared to classical neural networks. O…
Adaptor 'E' extends gradient-based optimizers to explore loss landscapes, improving generalization.
problem Finding lower and better-generalizing minima in deep learning.
method Proposes an adaptor 'E' to extend gradient-based optimizers, encouraging exploration along landscape valleys.
result Adapted optimizers increase test accuracy by an average of 2.5% in large-batch training tasks.
A simple continuous relaxation for argsort improves performance and is easy to implement.
problem Discrete nature of argsort operator makes it unsuitable for gradient-based learning.
method Proposed a continuous relaxation for argsort operator that is simple, fast, and achieves state-of-the-art performance.
result The proposed relaxation achieves state-of-the-art performance and is faster than competing approaches.
Review of gradient-based algorithms in statistical inference problems.
problem Understanding the dynamics of gradient-based algorithms in statistical inference.
method Insights from physics of glassy systems.
result Quantitative and qualitative understanding of algorithm performance.
SAP learns efficient task-specific parameter subspaces for few-shot learning.
problem Efficient few-shot learning with limited data.
method Subspace Adaptation Prior (SAP) learns task-specific parameter subspaces for efficient few-shot learning.
result SAP yields superior or competitive performance in few-shot image classification.
Gradient-based methods improve understanding of deep learning survival models.
problem Limited interpretability of deep learning survival models hinders their adoption.
method Gradient-based explanation methods tailored to survival neural networks.
result Gradient-based methods capture feature effects and temporal dynamics.
A new hyperparameter optimization method reduces overfitting.
problem Overfitting in hyperparameter optimization.
method PAC-Bayes bound minimization using gradient-based algorithm.
result Significant reduction in out-of-sample error.
Introduces new gradient-based methods for machine learning problems.
problem New challenges in machine learning due to decision-making and multi-agent problems.
method Gradient-based optimization and variational inequalities.
result Shifts focus from pattern recognition to decision-making and multi-agent problems.
Paper tackles co-generation with GANs, developing a new algorithm.
problem Inferring the most likely configuration for a subset of variables given the rest.
method Annealed Importance Sampling based Hamiltonian Monte Carlo algorithm.
result Significantly outperforms classical gradient based methods.
New gradient-based method learns causal structures from data.
problem Challenging task in causal structure learning.
method Graph Autoencoder framework for gradient-based optimization.
result Significantly outperforms other gradient-based methods on large causal graphs.
Unified analysis of stochastic ADMM variants via SME.
problem Analyzing and optimizing stochastic ADMM variants for machine learning.
method Unified mathematical framework of SME for continuous-time analysis.
result Dynamics of stochastic ADMM approximated by SDEs with small noise.
Multimodal MAML adapts faster to tasks from a diverse distribution.
problem Limitations of gradient-based meta-learners in learning from multimodal task distributions.
method Augmenting MAML with a capability to identify and adapt to tasks from a multimodal distribution.
result Multimodal MAML adapts faster to tasks from a multimodal distribution.
Bayesian Neural Networks are robust to gradient-based attacks in the large-data limit.
problem Vulnerability of deep learning models to adversarial attacks.
method Analysis of adversarial attacks in the large-data, overparametrized limit for Bayesian Neural Networks.
result BNN posteriors are robust to gradient-based adversarial attacks in the limit.
Proposes VSGD optimizer combining probabilistic and gradient-based methods.
problem Uncertainty modeling in deep neural networks.
method Combines probabilistic and gradient-based approaches using SVI.
result VSGD outperforms Adam and SGD on image classification tasks.
Gradient-based meta-RL fails with incorrect task distributions, leading to instability and poor performance.
problem Gradient-based meta-RL's sensitivity to task distributions causes instability and poor performance.
method Proposes meta Active Domain Randomization (meta-ADR) to learn task distributions for gradient-based meta-RL.
result Meta-ADR improves stability and generalization of MAML on simulated locomotion and navigation tasks.
We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally determini…
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
problem Resource constraints in deploying large language models (LLMs).
method IMPACT integrates activation importance into low-rank compression, optimizing for both size and accuracy.
result IMPACT achieves up to 55.4% greater model size reduction while maintaining comparable or better accuracy.
Avare improves optimization and sampling with adaptive importance sampling.
problem Improving convergence rate of stochastic gradient-based algorithms.
method Adaptive importance sampling with decreasing step-sizes.
result Achieves dynamic regret bounds of O(T2/3) and O(T5/6). New learning rate approach reveals phase transitions in SGD performance.
problem Understanding feature learning dynamics in neural networks.
method Characterizing the relationship between learning rate(s) and sample complexity for gradient-based algorithms.
result Phase transition from information exponent to generative exponent regime with different learning rates.
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
problem Gradient-based causal discovery methods can be biased by distributional asymmetries in bivariate categorical data.
method Identified and examined two distributional biases: Marginal Distribution Asymmetry and Marginal Distribution Shift Asymmetry. Employed two simple models to demonstrate and control these biases.
result Gradient-based methods can be biased by distributional asymmetries, and these biases can be controlled.
New algorithm improves gradient-based ERM for smooth convex losses.
problem Empirical risk minimization of smooth, strongly convex loss functions.
method Iterative gradient-based method with local polynomial regression.
result Oracle complexity of O((pε−1)d/(2η)) for our algorithm. Attention weights may not accurately highlight important parts due to combinatorial shortcuts.
problem Inaccurate interpretation of attention weights in models.
method Theoretical analysis and design of experiments to show combinatorial shortcuts. Proposed two methods to mitigate this issue.
result Proposed methods improve the interpretability of attention mechanisms.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not applicable to a number of important continuous distributions. We introduce an a…
Gradient-based MCMC for discrete spaces improves sampling performance.
problem Sampling in discrete spaces using traditional methods is challenging.
method Introduced new discrete Metropolis-Hastings samplers inspired by MALA, with a novel preconditioning technique.
result Demonstrated strong empirical performance across various challenging sampling problems.
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.