New federated learning protocols improve on knowledge distillation's poor performance.
problem Designing a universal API for federated learning without public data.
method Proposed Federated Kernel ridge regression using knowledge distillation.
result Performance of new protocols closely matches theoretical predictions.
L2R learns to denoise images without needing noise distribution knowledge.
problem Traditional denoising methods require noise distribution knowledge, limiting their applicability.
method L2R uses a learnable monotonic neural network to learn recorruption without distribution knowledge.
result L2R achieves state-of-the-art performance across various noise distributions.
This paper tackles continuous domain adaptation with a new approach.
problem Learning in non-stationary environments, especially domain drift.
method Variational domain-agnostic feature replay, composed of inference, generative, and solver modules.
result Demonstrates the effectiveness of the proposed approach for practical usage.
Paper analyzes error exponent in agnostic PAC learning.
problem Analyzing performance of agnostic PAC learning.
method Using error exponent from Information Theory to analyze PAC learning.
result Improved distribution-dependent error exponent for agnostic learning.
NSGD-M optimizes machine learning models without hyperparameter tuning, even under relaxed smoothness.
problem Training machine learning models with optimal complexity under relaxed smoothness assumptions.
method Normalized Stochastic Gradient Descent with Momentum (NSGD-M) without stepsize tuning.
result NSGD-M achieves nearly optimal complexity without prior knowledge of problem parameters.
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from…
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
NeAda solves nonconvex minimax optimization by balancing primal and dual variables adaptively.
problem Nonconvex minimax optimization challenges with parameter-agnostic adaptive algorithms.
method Nested Adaptive (NeAda) framework with inner and outer loops for primal and dual variables.
result Achieves near-optimal convergence rates for nonconvex-strongly-concave problems.
Framework evaluates the impact of prior knowledge in deep learning models.
problem Mitigating data-driven model shortcomings like data dependence and generalization ability.
method Model-agnostic framework inspired by interpretable machine learning, assessing data volume and estimation range effects.
result Complex relationship between data and knowledge, including dependence, synergistic, and substitution effects.
New algorithm reduces prediction error in online learning without knowing base measure.
problem Smoothed online learning without knowledge of base measure.
method R-Cover algorithm based on recursive coverings.
result First algorithm to guarantee sublinear regret for agnostic smoothed online learning without prior knowledge of base measure.
FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.
problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.
DACL tackles domain-specific contrastive learning by using Mixup noise.
problem Domain-specific contrastive learning methods rely on data augmentation techniques that require domain knowledge.
method DACL uses Mixup noise to create similar and dissimilar examples without domain-specific data augmentation.
result DACL outperforms other domain-agnostic noising methods and combines well with domain-specific methods.
New algorithms for linear bandits avoid norm knowledge, reducing regret.
problem Linear bandits require knowledge of norm bound S on parameter θ∗, leading to high regret. method Proposes two novel algorithms for changing and fixed arm sets, analyzing their regret bounds.
result Regret bounds show no significant price for not knowing S, with no price for fixed arm sets. New method improves convergence of RL meta-learning.
problem Improving convergence in model-agnostic meta-reinforcement learning.
method Proposes Stochastic Gradient Meta-Reinforcement Learning (SG-MRL) to find ε-first-order stationary points. result Derives iteration and sample complexity for SG-MRL.
i-Mix improves contrastive learning across domains without domain-specific augmentations.
problem Improving contrastive representation learning for unlabeled data across diverse domains.
method i-Mix treats contrastive learning as a non-parametric classifier problem, mixing data in input and virtual label spaces.
result i-Mix consistently improves representation quality across image, speech, and tabular data domains.
Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which have to be extensively …
Develops a transparent surrogate model for complex data.
problem Balancing accuracy and transparency in complex decision-making models.
method Partial dependence effects for feature engineering, smart segmentation, and GLM fitting.
result The maidrr GLM closely approximates a black box model and outperforms benchmarks.
In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resource-constrained during inference. A popular approach to reduce the size of a deep learning architecture consists in distilling knowledge from…
Proposes a method to use causal graph knowledge for better predictive modeling.
problem Lack of effective ways to incorporate causal graph knowledge into predictive models.
method Model-agnostic data augmentation method exploiting CI relations encoded in causal graphs.
result Improves prediction accuracy, especially in small-data scenarios.
This paper improves understanding of knowledge distillation and its effects.
problem Improving model quality with a fixed capacity budget.
method Categorizing teacher's knowledge into three levels and studying their effects on distillation.
result The three hierarchical levels of teacher's knowledge (universe, domain, instance) significantly impact knowledge distillation.
Task-agnostic data valuation without validation requirements.
problem Valuing data without specific task assumptions.
method Estimating data diversity and relevance through queries without raw data.
result Estimates capture the diversity and relevance of seller's data for the buyer.
New method prevents forgetting in learning new tasks.
problem Learning new tasks without forgetting old knowledge.
method Hierarchical information-theoretic optimality principle and Mixture-of-Variational-Experts layer.
result Our method can operate task-agnostically and improve performance in various learning problems.
The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited …
While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data strea…
In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain cla…
Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
problem Minimax estimators may be inadmissible under structure-agnostic models.
method Exhibit second-order (U-statistic) estimators that asymptotically dominate DML estimators.
result Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
New theory controls compression change probability without prior knowledge.
problem Controlling compression change probability without prior knowledge.
method New theory on compression function and statistical risk.
result Cardinality of compressed set is a consistent estimator of probability of change of compression.
Improves prediction stability with model misspecification and distribution shift.
problem Inaccurate parameter estimation and instability of prediction in real-world applications.
method Proposes Decorrelated Weighting Regression (DWR) algorithm to optimize weights for samples and variables.
result Significantly improves accuracy of parameter estimation and prediction stability.
New algorithm learns from sparse data without knowing sparsity index.
problem Sparse bandit problem where only a subset of features affects reward.
method Sparsity-agnostic Lasso Bandit algorithm that doesn't require prior sparsity index knowledge.
result Established tight regret bounds and outperforms existing methods.
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…
A dataset for evaluating engagement with scientific video lectures.
problem Challenges in managing learning resources due to rapid creation of video lectures.
method Introduction of VLEngagement dataset with content-based and video-specific features, and metrics related to user engagement.
result The largest and most diverse publicly available dataset for understanding context-agnostic engagement in video lectures.
Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its precise, rigorous foundation: it provides a common, model-agnostic language for AI e…
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correct…
Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new programming languages, libraries, and functionalities. Comprehensive labeling of sou…
Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen clas…
Method detects new physics signals without prior knowledge.
problem Selecting signal regions for novel particles.
method Model-agnostic approach using low-pass filtering and density estimation.
result Efficiently identifies data-driven signal regions in high-dimensional feature space.
Proposes a framework for generating explainable AI exemplars.
problem Need to explain decisions of complex deep learning models.
method Generative model with evolutionary strategy to synthesize exemplars.
result Framework is generic and model-agnostic for various data types.
First proper learning algorithm for Gaussian halfspaces with matching sample and computational complexity.
problem Agnostically learning halfspaces under Gaussian distribution.
method First proper learning algorithm with matching sample and computational complexity.
result First proper learning algorithm for agnostically learning halfspaces under Gaussian distribution with matching sample and computational complexity.
TiAda adapts adaptive gradient methods for nonconvex minimax optimization.
problem Nonconvex minimax optimization challenges in achieving convergence.
method TiAda is a time-scale adaptive GDA algorithm for nonconvex minimax optimization.
result TiAda achieves near-optimal complexities in deterministic and stochastic settings.
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
problem Estimating unknown parameters in hybrid models combining machine learning and scientific models.
method Sharpness-aware minimization adapted for hybrid modeling, focusing on model simplicity.
result Demonstrates effectiveness of SAM-based hybrid model learning for scientific parameter estimation.
GACBO optimizes unknown causal graphs with interventions.
problem Optimizing a target variable on an unknown causal graph with interventions.
method Graph Agnostic Causal Bayesian Optimisation (GACBO) seeks to balance exploitation and exploration of causal structures and functions.
result GACBO outperforms baselines in simulated and real-world applications.
In this paper we study the setting where features are added or change interpretation over time, which has applications in multiple domains such as retail, manufacturing, finance. In particular, we propose an approach to provably determine the time instant from which the new/changed features start becoming relevant with…
New approach makes deep reinforcement learning robust without assuming adversary knowledge.
problem Deep reinforcement learning policies are vulnerable to state observation perturbations.
method Proposes an adversary agnostic robust DRL paradigm using policy distillation with two terms: prescription gap maximization and Jacobian regularization.
result Boosts adversarial robustness on five Atari games compared to state-of-the-art methods.
This work considers an estimation task in compressive sensing, where the goal is to estimate an unknown signal from compressive measurements that are corrupted by additive pre-measurement noise (interference, or clutter) as well as post-measurement noise, in the specific setting where some (perhaps limited) prior knowl…
Sharp-MAML improves MAML by reducing saddle points in few-shot learning.
problem Challenges in optimizing MAML due to complex loss landscape.
method Sharpness-aware minimization applied to MAML.
result Sharp-MAML and its variant outperform plain MAML on few-shot learning tasks.
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards. This algorithm combines an efficient bandit algorithm, kl-UCB, with an efficient, parameter-free, changepoint detector, the Bernoulli Generalized Likelihood Ratio Test, for which we provide new theoretica…