RIDM combines imitation and RL with a single demo, no action info needed.
problem Learning from a single observed demonstration without action information.
method Reinforced Inverse Dynamics Modeling (RIDM) that operates on raw state features.
result RIDM performs favorably compared to baseline on simulated and real tasks.
Paper tackles catastrophic overfitting in single-step adversarial training.
problem Catastrophic overfitting leads to sudden drop in robust accuracy.
method Proposes a method to prevent overfitting by using all adversarial examples.
result Demonstrates prevention of catastrophic overfitting and improves robustness.
Method learns from video demonstrations with human feedback.
problem Teaching autonomous agents using video demonstrations and human feedback.
method Constructs a mapping between standard and visual representations using a neural network.
result Effective in teaching a hopper agent to perform a backflip with minimal human feedback.
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of …
Proposes CCCVAE for better single-cell clustering with cell-cell communication.
problem Improving single-cell RNA sequencing clustering by incorporating cell-cell communication.
method Integrates cell-cell communication into a variational autoencoder framework.
result Empirical results show CCCVAE outperforms standard VAEs in clustering performance.
Improved GPLVM model for single-cell RNA-seq data.
problem Lack of effective scalable models for clustering cell types in large-scale single-cell RNA-seq data.
method Introduces amortized stochastic variational Bayesian GPLVM (BGPLVM) tailored for single-cell RNA-seq.
result Matches the performance of scVI on synthetic and real-world datasets and reveals more interpretable latent structures.
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge us…
Kernel testing compares cell states in single-cell data.
problem Comparing non-linear cell states in single-cell data.
method Kernel-based testing framework for non-linear distribution comparison.
result Identifies subtle population variations in cell states.
ES-Single uses ES to estimate gradients in unrolled graphs, reducing variance and improving performance.
problem Estimating gradients in unrolled computation graphs with low variance and stability.
method Evolution strategies (ES) applied to unrolled graphs, with a single perturbation per particle.
result ES-Single reduces variance compared to PES, leading to better performance in various tasks.
Lookahead pruning extends single-layer optimization to multi-layer, outperforming magnitude-based pruning.
problem Pruning neural networks to reduce computational cost and memory usage.
method Developed a multi-layer optimization approach extending the single-layer optimization of magnitude-based pruning.
result Consistently outperforms magnitude-based pruning on various networks, especially in high sparsity.
New algorithm optimizes matrix reordering for noisy disordered matrices.
problem Optimizing matrix reordering for noisy disordered matrices in single-cell biology and metagenomics.
method Proposed a polynomial-time adaptive sorting algorithm to improve upon spectral seriation.
result Our algorithm achieves superior performance compared to existing methods in real datasets.
Study finds methods to learn multiple solutions from single task in offline RL.
problem Learning multiple solutions from a single task in offline RL.
method Proposed algorithms for offline RL.
result Empirical results show learning of multiple solutions in offline RL.
Kernel methods estimate causal effects with a single proxy for deterministic confounders.
problem Estimating causal effects with a single proxy for an unobserved confounder.
method Two kernel-based methods: two-stage regression and maximum moment restriction.
result Both kernel methods can consistently estimate the causal effect.
Gradient descent struggles with learning a single neuron with bias.
problem Learning a single neuron with a bias term in the realizable setting with ReLU activation.
method Theoretical study using gradient descent, characterizing critical points, and providing convergence guarantees.
result Gradient descent faces significant challenges in learning a single neuron with bias, unlike the bias-less case.
Scaling up model and data size improves imitation learning in single-agent games.
problem Limited recovery of expert behavior in single-agent games using imitation learning.
method Investigate the effect of scaling model and data size on imitation learning performance.
result IL loss and mean return scale with compute budget, resulting in power laws.
New analysis shows actor-critic method converges efficiently in practical settings.
problem Understanding finite-time convergence of single-timescale actor-critic methods.
method Investigated online single-timescale actor-critic algorithm with linear function approximation and Markovian sampling.
result Proved convergence to ε-approximate stationary point with sample complexity of O(ε^(-2)).
Study improves robustness of deep fusion models against single source noise.
problem Ensuring robustness of deep fusion models against noise added to a single input source.
method Proposed two approaches: a carefully designed loss function and a convolutional fusion layer.
result Deep fusion models become robust against noise applied to a single source, preserving performance on clean data.
A model learns rewards from diverse demonstrations for structurally similar tasks.
problem Difficulty in learning reward functions from demonstrations in real-world applications.
method Deep latent variable model that infers rewards from heterogeneous demonstrations of related tasks.
result Model can infer rewards for new tasks from a single demonstration.
SSFI identifies key features affecting a single data point's prediction.
problem Understanding feature importance for a single data point.
method Interpretable algorithm using Random Forest's prediction path.
result Relative ranking of features impacting a data point's prediction.
Study SGD dynamics in sequence models, revealing training phases and influence of sequence length.
problem Understanding SGD in sequence models like attention networks.
method Derived closed-form population loss and analyzed SGD dynamics for SSI models.
result Two distinct training phases: escape from uninformative initialization and alignment with target subspace.
SGD shows distinct phases in learning single-index models, achieving optimal sample complexity and regret.
problem Learning single-index models with SGD in adaptive data settings.
method Stochastic gradient descent (SGD) with an optimal learning rate schedule.
result SGD achieves near-optimal sample complexity and regret guarantees across both burn-in and learning phases.
We present a multi-task learning approach to jointly estimate the means of multiple independent data sets. The proposed multi-task averaging (MTA) algorithm results in a convex combination of the single-task maximum likelihood estimates. We derive the optimal minimum risk estimator and the minimax estimator, and show t…
The paper develops methods for causal inference from single-cell RNA sequencing data with multiple outcomes.
problem Causal inference from single-cell RNA sequencing data with multiple heterogeneous outcomes.
method Generic semiparametric inference framework for doubly robust estimation with multiple derived outcomes.
result Demonstrates the use of semiparametric inferential results for estimating causal effects in genomics.
We propose a new method for learning from a single demonstration to solve hard exploration tasks like the Atari game Montezuma's Revenge. Instead of imitating human demonstrations, as proposed in other recent works, our approach is to maximize rewards directly. Our agent is trained using off-the-shelf reinforcement lea…
Estimates joint causal effects using single-variable interventions on nonlinear models.
problem Estimating joint causal effects from single-variable interventions.
method Identifiability result and practical estimator for decomposing causal effects.
result Joint effects can be inferred without joint interventional data for nonlinear additive models.
Standard myopic active learning assumes that human annotations are always obtainable whenever new samples are selected. This, however, is unrealistic in many real-world applications where human experts are not readily available at all times. In this paper, we consider the single shot setting: all the required samples s…
Forest Fire Clustering discovers cell types from single-cell data.
problem Discovering cell types from large-scale single-cell sequencing data.
method Iterative label propagation and parallelized Monte Carlo simulation.
result Forest Fire Clustering outperforms state-of-the-art methods on diverse benchmarks.
Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single…
SAFLe solves federated learning's trade-off between non-linearity and scalability.
problem Federated Learning's high communication overhead and performance collapse on non-IID data.
method SAFLe introduces a structured head of bucketed features and sparse, grouped embeddings, mathematically equivalent to a high-dimensional linear regression.
result SAFLe achieves a new state-of-the-art in analytic FL, outperforming linear AFL and multi-round DeepAFL.
New method defends against both single-step and iterative adversarial examples.
problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.
ChemCPA predicts cellular responses to novel drugs using transfer learning.
problem Scaling high-throughput screens to measure cellular responses for many drugs is costly and challenging.
method ChemCPA, a new encoder-decoder architecture combined with transfer learning.
result Training on existing bulk RNA HTS datasets improves generalization performance, reducing the need for extensive single-cell screens.
New method uses surrogate outcomes and single-record data to improve suicide risk modeling.
problem Lack of historical information in single-record patients hinders modeling rare medical events.
method Hybrid framework combining supervised and unsupervised learning to integrate concurrent and single-record data.
result Single-record data and concurrent diagnoses provide valuable information for improving suicide risk modeling.
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context…
Multi-head attention outperforms single-head in in-context linear regression tasks.
problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.
New methods improve analysis of single cell RNA sequencing data.
problem High dimensionality and complexity of scRNA-seq data.
method Topological Nonnegative Matrix Factorization (TNMF) and Robust Topological NMF (rTNMF).
result TNMF and rTNMF significantly outperform other NMF-based methods.
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
scICML integrates multi-omics data from single cells using co-clustering.
problem High noise and sparsity in multi-omics data from single cells.
method Information-theoretic co-clustering-based multi-view learning.
result Improves clustering performance and provides biological insights.
New method learns multi-class from single-class data with confidences.
problem Learning multi-class from single-class data without additional data.
method Empirical risk minimization framework for multi-class classification.
result Method achieves Bayes-consistency with noisy confidences.
Overparameterized ensembles don't offer generalization benefits over single large models.
problem Theoretical limitations of ensembles in overparameterized settings.
method Using ensembles of random feature (RF) regressors, the paper clarifies how modern ensembles differ from underparameterized counterparts.
result Infinite ensembles of overparameterized RF regressors become pointwise equivalent to single infinite-width RF regressors, and finite width ensembles converge to single models with the same parameter budget.
New algorithm reduces regret for single-index bandits to nearly optimal.
problem Optimizing rewards from unknown projections of high-dimensional contexts.
method Two-phase algorithm: estimate projection direction, reduce to 1D bandit, use UCB.
result Achieved optimal regret of ildeO(T2/3). A single robust classifier handles complex image synthesis tasks.
problem Challenging image synthesis tasks.
method Adversarial robustness training of a single classifier.
result Direct manipulation of salient features in input images.
Improved regret for single-index bandits with optimal algorithm.
problem Optimizing rewards from unknown one-dimensional projections of high-dimensional contexts.
method Two-phase algorithm: first estimate projection direction, then discretize and use UCB.
result Achieved optimal regret of ildeO(T2/3). A new method reduces adversarial training time without overfitting.
problem Catastrophic overfitting in single-step adversarial training.
method FGSMPR: FGSM with PGD Regularization.
result Reduces the gap to multi-step adversarial training.
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varyi…
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of networks which generalize and those which do not remain unclear. Additionally, the tuning properties of single directions (defined as the activa…
A new pyramidal diffusion model speeds up image generation.
problem Training and evaluating diffusion models are time-consuming.
method Introduces a pyramidal diffusion model with a single score function.
result Generates high-resolution images from low-resolution starting points efficiently.
All anti-self-dual Einstein metrics with non-zero cosmological constant arise from a single second-order PDE.
problem Anti-self-dual Einstein metrics with non-zero cosmological constant
method A second-order PDE introduced by Lipstein and Nagy
result All such metrics arise from this equation