Search Results for author:
Found 41 papers, 27 papers with code
Can a Bayesian Oracle Prevent Harm from an Agent?
With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification.
On Generalization for Generative Flow Networks
This paper attempts to formalize generalization in the context of GFlowNets, to link generalization with stability, and also to design experiments that assess the capacity of these models to uncover unseen parts of the reward function.
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem.
Learning diverse attacks on large language models for robust red-teaming and safety tuning
Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs).
Machine learning and information theory concepts towards an AI Mathematician
The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning.
Discrete Probabilistic Inference as Control in Multi-path Environments
We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process proportionally to some predefined reward.
V-STaR: Training Verifiers for Self-Taught Reasoners
Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability.
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
Improved off-policy training of diffusion samplers
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function.
PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
The proposed approach enables the estimation of the probability that two sets of samples are drawn from the same distribution, providing a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models trained on the same dataset.
Improving Gradient-guided Nested Sampling for Posterior Inference
We present a performant, general-purpose gradient-guided nested sampling algorithm, ${\tt GGNS}$, combining the state of the art in differentiable programming, Hamiltonian slice sampling, clustering, mode separation, dynamic nested sampling, and parallelization.
PhyloGFN: Phylogenetic inference with generative flow networks
Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities.
Amortizing intractable inference in large language models
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions.
Expected flow networks in stochastic environments and two-player zero-sum games
Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution.
Delta-AI: Local objectives for amortized inference in sparse graphical models
We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\Delta$-AI).
Discrete, compositional, and symbolic representations through attractor dynamics
Compositionality is an important feature of discrete symbolic systems, such as language and programs, as it enables them to have infinite capacity despite a finite symbol set.
Simulation-free Schrödinger bridges via score and flow matching
We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions.
Thompson sampling for improved exploration in GFlowNets
Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy.
BatchGFN: Generative Flow Networks for Batch Active Learning
We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward.
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space.
GFlowNet-EM for learning compositional latent variable models
Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents.
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an energy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood).
Improving and generalizing flow-based generative models with minibatch optimal transport
CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models.
A theory of continuous generative flow networks
Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects.
Posterior samples of source galaxies in strong gravitational lenses with score-based priors
Inferring accurate posteriors for high-dimensional representations of the brightness of gravitationally-lensed sources is a major challenge, in part due to the difficulties of accurately quantifying the priors.
GFlowOut: Dropout with Generative Flow Networks
These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation.
ThinkSum: Probabilistic reasoning over sets using large language models
Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs.
GFlowNets and variational inference
This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs.
Learning GFlowNets from partial episodes for improved convergence and stability
Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks.
Unifying Generative Models with GFlowNets and Beyond
Our framework provides a means for unifying training and inference algorithms, and provides a route to shine a unifying light over many generative models.
Diffusion models as plug-and-play priors
We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional information $\mathbf{y}$.
Resolving label uncertainty with implicit posterior models
We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label.
Generative Flow Networks for Discrete Probabilistic Modeling
We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data.
Trajectory balance: Improved credit assignment in GFlowNets
Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or strings, from a given unnormalized density by sequences of actions, where many possible action sequences may lead to the same object.
Coherence boosting: When your pretrained language model is not paying enough attention
Long-range semantic coherence remains a challenge in automatic language generation and understanding.
Resolving label uncertainty with implicit generative models
In prediction problems, coarse and imprecise sources of input can provide rich information about labels, but are not readily used by discriminative learners.
Studying word order through iterative shuffling
As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax.
GPT Perdetry Test: Generating new meanings for new words
Human innovation in language, such as inventing new words, is a challenge for pretrained language models.
High-resolution land cover change from low-resolution labels: Simple baselines for the 2021 IEEE GRSS Data Fusion Contest
We present simple algorithms for land cover change detection in the 2021 IEEE GRSS Data Fusion Contest.
Mining self-similarity: Label super-resolution with epitomic representations
We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks.
Shuffle relations for Hodge and motivic correlators
Motivic correlators have several advantages: they obey dihedral symmetry relations at all points, not only at roots of unity; they are defined for any curve, and the double shuffle relations admit a generalization to elliptic curves; and they describe elements of the motivic Lie coalgebra rather than its universal enveloping algebra.
Algebraic Geometry
