Search Results for author:
Found 42 papers, 19 papers with code
Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
In some cases, it is even better than training on all data from the target group, because it leverages the diversity and size of a larger training set.
Budgeting Counterfactual for Offline RL
The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action?
Taming AI Bots: Controllability of Neural States in Large Language Models
We then characterize the subset of meanings that can be reached by the state of the LLMs for some input prompt, and show that a well-trained bot can reach any meaning albeit with small probability.
Learning Capacity: A Measure of the Effective Dimensionality of a Model
We exploit a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to define a "learning capacity'' which is a measure of the effective dimensionality of a model.
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training.
Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis
This work analyzes how the backward error affects the diffusion ODEs and the sample quality in DDPMs.
Mesh Strikes Back: Fast and Efficient Human Reconstruction from RGB videos
Human reconstruction and synthesis from monocular RGB videos is a challenging problem due to clothing, occlusion, texture discontinuities and sharpness, and framespecific pose changes.
A picture of the space of typical learnable tasks
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning.
Learning under Data Drift with Time-Varying Importance Weights
Real-world deployment of machine learning models is challenging because data evolves over time.
The Value of Out-of-Distribution Data
In this work, we show a counter-intuitive phenomenon: the generalization error of a task can be a non-monotonic function of the number of OOD samples.
Beyond mAP: Towards better evaluation of instance segmentation
Correctness of instance segmentation constitutes counting the number of objects, correctly localizing all predictions and classifying each localized prediction.
MammoDL: Mammographic Breast Density Estimation using Federated Learning
Assessing breast cancer risk from imaging remains a subjective process, in which radiologists employ simple computer aided detection (CAD) systems or qualitative visual assessment to estimate breast percent density (PD).
Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies
Despite the great promise that machine learning has offered in many fields of medicine, it has also raised concerns about potential biases and poor generalization across genders, age distributions, races and ethnicities, hospitals, and data acquisition equipment and protocols.
Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity
In order to empower NAM with feature selection and improve the generalization, we propose the sparse neural additive models (SNAM) that employ the group sparsity regularization (e. g. Group LASSO), where each feature is learned by a sub-network whose trainable parameters are clustered as a group.
Deep Reference Priors: What is the best way to pretrain a model?
Such priors enable the task to maximally affect the Bayesian posterior, e. g., reference priors depend upon the number of samples available for learning the task and for very small sample sizes, the prior puts more probability mass on low-complexity models in the hypothesis space.
Prospective Learning: Principled Extrapolation to the Future
We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning.
Does the Data Induce Capacity Control in Deep Learning?
This structure is mirrored in a network trained on this data: we show that the Hessian and the Fisher Information Matrix (FIM) have eigenvalues that are spread uniformly over exponentially large ranges.
Model Zoo: A Growing Brain That Learns Continually
This paper argues that continual learning methods can benefit by splitting the capacity of the learner across multiple models.
Harmonization with Flow-based Causal Inference
Heterogeneity in medical data, e. g., from data collected at different sites and with different protocols in a clinical study, is a fundamental hurdle for accurate prediction using machine learning models, as such models often fail to generalize well.
Model Zoo: A Growing "Brain" That Learns Continually
We use statistical learning theory and experimental analysis to show how multiple tasks can interact with each other in a non-trivial fashion when a single model is trained on them.
Ranked #1 on
Continual Learning
on Cifar100 (20 tasks)
Deformable Linear Object Prediction Using Locally Linear Latent Dynamics
We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.
Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
We can also tackle situations where we do not have access to ground-truth labels on target data; we show how one can use auxiliary tasks for adaptation; these tasks employ covariates such as age, gender and race which are easy to obtain but nevertheless correlated to the main task.
Continuous Doubly Constrained Batch Reinforcement Learning
Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration.
Scalable Reinforcement Learning Policies for Multi-Agent Control
Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
An Information-Geometric Distance on the Space of Tasks
Using tools in information geometry, the distance is defined to be the length of the shortest weight trajectory on a Riemannian manifold as a classifier is fitted on an interpolated task.
MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road.
Proximal Deterministic Policy Gradient
This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms.
DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning
This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity.
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
Automated machine learning (AutoML) can produce complex model ensembles by stacking, bagging, and boosting many individual models like trees, deep networks, and nearest neighbor estimators.
BayesRace: Learning to race autonomously using prior experience
Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle's handling capability.
TraDE: Transformers for Density Estimation
We present TraDE, a self-attention-based architecture for auto-regressive density estimation with continuous and discrete valued data.
A Free-Energy Principle for Representation Learning
This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learnt representations for transfer learning.
Rethinking the Hyperparameters for Fine-tuning
Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.
Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications
Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points.
Meta-Q-Learning
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL).
A Baseline for Few-Shot Image Classification
When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters.
P3O: Policy-on Policy-off Policy Optimization
Extensive experiments on the Atari-2600 and MuJoCo benchmark suites show that this simple technique is effective in reducing the sample complexity of state-of-the-art algorithms.
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
So SGD does perform variational inference, but for a different loss than the one used to compute the gradients.
Parle: parallelizing stochastic gradient descent
We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters.
Deep Relaxation: partial differential equations for optimizing deep neural networks
In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs).
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape.
On the energy landscape of deep networks
Specifically, we show that a regularization term akin to a magnetic field can be modulated with a single scalar parameter to transition the loss function from a complex, non-convex landscape with exponentially many local minima, to a phase with a polynomial number of minima, all the way down to a trivial landscape with a unique minimum.
