Searcharxiv⌕ Search

arXiv subjects

Alexandre Galashov

Publications and source records attributed to Alexandre Galashov.

At least 19 recordsLinked to original sources
arXiv2026

Sampling Interventional Distributions with Orthogonal MMD Flow

Many causal inference problems require sampling from interventional outcome distributions rather than estimating low-dimensional summaries. Existing approaches often rely on fitting generative models of the target distribution together with additional nuisance components, which can be computationally demanding for high-dimensional outcomes. We propose Interventional Maximum Mean Discrepancy Flow (IMMD-Flow), a particle-based method that instead represents the target interventional distribution through its kernel mean embedding. This kernel embedding admits a doubly robust, Neyman-orthogonal estimator with finite-sample guarantees and can be efficiently reused to sample from the interventional distribution via MMD gradient flow. IMMD-Flow accommodates both hard and soft interventions, admits theoretical guarantees for estimation and particle approximation, and extends to high-dimensional image outcomes through frozen encoders. Across image-based benchmarks, IMMD-Flow matches or improves upon state-of-the-art generative approaches while showing significant speed advantages.

cs.LG↗
arXiv2026

Doubly Robust Proxy Causal Learning with Neural Mean Embeddings

We propose a novel doubly robust neural mean-embedding framework for proxy causal learning (PCL) for continuous and structured treatments. PCL uses proxy variables and bridge functions to identify causal effects under unobserved confounding: either an outcome bridge or a treatment bridge can identify the target, while doubly robust methods combine both. Our framework learns both bridges with data-adaptive neural features and combines them into doubly robust estimators of population, treatment-conditional, and heterogeneous dose-response functions. Two features of our result are particularly notable: the treatment bridge can be learned without density ratios, and the same treatment bridge yields both population and heterogeneous responses, eliminating the need for a separate bridge fit. Our analysis shows that the doubly robust error is controlled by final-stage error and the smaller of the two projected bridge errors, with no separate density-ratio estimation error. Across challenging continuous- and structured-treatment benchmarks, our method outperforms neural single-bridge estimators and fixed-feature doubly robust estimators. Our implementation is available at https://github.com/BariscanBozkurt/DoublyRobust-PCL-Network.

cs.LG↗
arXiv2026

Improved Distributional Diffusion Models

Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a \emph{distributional} denoiser trained via a scoring rule objective, learning a stochastic approximation to $p(x_1 \mid x_t)$ rather than its conditional mean. However, scaling DDMs to modern image-generation settings faces two obstacles: (i) multi-particle training incurs overhead that scales with the number of particles, (ii) DDMs use globally fixed scoring rule hyperparameters, forcing a single trade-off across sampling budgets. We mitigate these limitations by deferring particle expansion to late transformer layers, and the hyperparameter trade-off by introducing time-dependent scoring rule schedules informed by the dynamical regimes of~\citet{Biroli2024}. Combined with a DiT-based latent setup, these changes make DDM training practical on class-conditional ImageNet-$256^2$, achieving 4.48 FID at 4 steps and 2.38 at 50 steps with DiT-XL/2, from a single model trained from scratch in one stage, without a teacher, self-distillation or JVPs. The result is a stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation. Code and pre-trained models available at https://github.com/CompVis/iDDM.

cs.CV↗
arXiv2026

Simplex Diffusion Models

Diffusion models have revolutionized generative modeling for continuous data through the gradual refinement of a belief state. This iterative refinement has not yet carried over to discrete diffusion models, which discard uncertainty at intermediate steps through categorical sampling (information collapse). We propose Simplex Diffusion Models (SDMs), a framework that lifts the diffusion process to the probability simplex to represent beliefs over categories. SDMs admit probability paths with closed-form reverse transitions and can be trained with a simple cross-entropy loss. Contrary to earlier proposals such as Dirichlet Flow Matching which requires integrating an ordinary differential equation, we introduce a DDIM-like sampler with a tunable level of stochasticity. Because SDMs operate on samples on the simplex, they can carry uncertainty across denoising steps, which mitigates information collapse. On OpenWebText, SDMs are competitive with strong Discrete Diffusion baselines, achieving $17.0$ GenPPL at $5.46$ unigram entropy in 64 sampling steps, close to real validation data. Even without Self-Conditioning (SC), SDMs outperform masked and uniform diffusion (with SC or predictor-corrector sampling) on code generation (TinyGSM, $T=0.1$; $49.0\%$ vs. $45.8\%$). Distilled down to 8 steps, SDMs solve $32.1\%$ of GSM8K problems, more than distilled Discrete Diffusion models with 128 steps ($21.4\%$).

cs.LG↗
arXiv2026

Adversarial Learning of Classifier-Free Guidance Schedules

Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is generally suboptimal and can introduce artifacts, as different states may benefit from different levels of guidance. While time-varying schedules are known to improve quality, designing them by hand is non-trivial and application-dependent. In this paper, we learn the guidance schedule as a function of diffusion time, conditioning and the current noisy sample, in order to better align sampled images with the text prompt. We frame this as a density ratio estimation problem: a discriminator is trained to estimate the time-dependent log-density ratio between the true and guided marginal distributions, while a lightweight generator network predicts the optimal, state-dependent guidance scale. Empirically, our approach outperforms both heuristic CFG schedules and prior methods for learning dynamic guidance on text-to-image generation benchmarks.

cs.LG↗
arXiv2026

DiffusionGemma Technical Report

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional autoregressive (AR) large language models. Instead of training from scratch, we obtain DiffusionGemma by fine-tuning the mixture-of-experts Gemma 4 model with 3.8B activated and 25.2B total parameters. Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget. The first stage uses supervised fine-tuning to teach bidirectional denoising, while the second stage combines reinforcement learning with sampler distillation to jointly improve generation quality and inference efficiency. DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. Averaged across our full evaluation suite, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU, which is substantially faster than AR models even with state-of-the-art speculative decoding. DiffusionGemma also retains the starting model's support for thinking mode, multimodal inputs, and long contexts. Despite diffusion fine-tuning, it remains capable of AR generation with only minor performance degradation, suggesting a path toward hybrid diffusion-AR decoding.

cs.CL↗
arXiv2026

On the Wasserstein Gradient Flow Interpretation of Drifting Models

Recently, Deng et al. (2026) proposed Generative Modeling via Drifting (GMD), a novel framework for generative tasks. This note presents an analysis of GMD through the lens of Wasserstein Gradient Flows (WGF), i.e., the path of steepest descent for a functional in the space of probability measures, equipped with the geometry of optimal transport. Unlike previous WGF-based contributions, GMD can be thought of as directly targeting a fixed point of a specific WGF flow. We demonstrate three main results: first, that one algorithm proposed by Deng et al. (2026) corresponds to finding the limiting point of a WGF on the KL divergence, with Parzen smoothing on the densities. Second, that the algorithm actually implemented by Deng et al. (2026) corresponds to a different procedure, which bears some resemblance to the fixed point of a WGF on the Sinkhorn divergence, but lacks certain desirable properties of the latter. Third, the same same idea can be extended to the limiting point of other WGFs, including the Maximum Mean Discrepancy (MMD), the sliced Wasserstein distance, and GAN critic functions.

cs.LG↗
arXiv2026

Closed-Form Last Layer Optimization

Neural networks are typically optimized with variants of stochastic gradient descent. Under a squared loss, however, the optimal solution to the linear last layer weights is known in closed-form. We propose to leverage this during optimization, treating the last layer as a function of the backbone parameters, and optimizing solely for these parameters. We show this is equivalent to alternating between gradient descent steps on the backbone and closed-form updates on the last layer. We adapt the method for the setting of stochastic gradient descent, by trading off the loss on the current batch against the accumulated information from previous batches. We provide theoretical analyses showing convergence of the method to an optimal solution in the neural tangent kernel regime, as well as quantifying the gains compared to standard SGD in a one-step analysis. Finally, we demonstrate the effectiveness of our approach compared with SGD and Adam on a squared loss in several regression tasks, including neural operators and causal inference.

cs.LG↗
arXiv2026

Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production

Within the landscape of inference-time scaling methods for foundation models, a width-based approach to scaling -- which involves the insertion of tokens in the input stream to delay model responses -- offers a unique advantage by increasing model expressivity while remaining highly parallelizable at both training and inference. The existing literature on training models to utilize tokens relies on the standard cross-entropy objective in which the model output is read out and evaluated only at the final step of a pause sequence. This approach provides no mechanism for the model to regulate its own processing or to signal readiness to respond, treating the additional compute steps as a static barrier rather than a resource to be used adaptively. We propose a supervised loss, Catch Your Breath (CYB), framed as a sequential-decision problem, that trains a model to dynamically and autonomously scale the number of compute steps used for each input token. The model indicates the need for additional compute steps by emitting a special output, delaying its response via a pause. The model can abstain multiple times to obtain longer delays. Our experiments demonstrate that CYB significantly outperforms standard cross-entropy when introduced either in pretraining or fine-tuning, reducing perplexity and enhancing downstream accuracy with no additional computational or memory cost.

cs.CL↗
arXiv2025

Learn to Guide Your Diffusion Model

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates using a guidance weight $ω$. While a large, static weight can markedly improve visual results, this often comes at the cost of poorer distributional alignment. In order to better approximate the target conditional distribution, we instead learn guidance weights $ω_{c,(s,t)}$, which are continuous functions of the conditioning $c$, the time $t$ from which we denoise, and the time $s$ towards which we denoise. We achieve this by minimizing the distributional mismatch between noised samples from the true conditional distribution and samples from the guided diffusion process. We extend our framework to reward guided sampling, enabling the model to target distributions tilted by a reward function $R(x_0,c)$, defined on clean data and a conditioning $c$. We demonstrate the effectiveness of our methodology on low-dimensional toy examples and high-dimensional image settings, where we observe improvements in Fréchet inception distance (FID) for image generation. In text-to-image applications, we observe that employing a reward function given by the CLIP score leads to guidance weights that improve image-prompt alignment.

cs.LG↗
arXiv2025

Distributional Diffusion Models with Scoring Rules

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively "denoises" a Gaussian sample into a sample from the data distribution. However, generating high-quality outputs requires many discretization steps to obtain a faithful approximation of the reverse process. This is expensive and has motivated the development of many acceleration methods. We propose to accomplish sample generation by learning the posterior {\em distribution} of clean data samples given their noisy versions, instead of only the mean of this distribution. This allows us to sample from the probability transitions of the reverse process on a coarse time scale, significantly accelerating inference with minimal degradation of the quality of the output. This is accomplished by replacing the standard regression loss used to estimate conditional means with a scoring rule. We validate our method on image and robot trajectory generation, where we consistently outperform standard diffusion models at few discretization steps.

cs.LG↗
arXiv2025

Accelerated Diffusion Models via Speculative Sampling

Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While speculative sampling was previously limited to discrete sequences, we extend it to diffusion models, which generate samples via continuous, vector-valued Markov chains. In this context, the target model is a high-quality but computationally expensive diffusion model. We propose various drafting strategies, including a simple and effective approach that does not require training a draft model and is applicable out of the box to any diffusion model. Our experiments demonstrate significant generation speedup on various diffusion models, halving the number of function evaluations, while generating exact samples from the target model.

cs.LG↗
arXiv2024

Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset

Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popular; examples include supervised learning under distributional shifts, reinforcement learning, continual learning and non-stationary contextual bandits. In this work we introduce a novel learning approach that automatically models and adapts to non-stationarity, via an Ornstein-Uhlenbeck process with an adaptive drift parameter. The adaptive drift tends to draw the parameters towards the initialisation distribution, so the approach can be understood as a form of soft parameter reset. We show empirically that our approach performs well in non-stationary supervised and off-policy reinforcement learning settings.

cs.LG↗
arXiv2024

Deep MMD Gradient Flow without adversarial training

We propose a gradient flow procedure for generative modeling by transporting particles from an initial source distribution to a target distribution, where the gradient field on the particles is given by a noise-adaptive Wasserstein Gradient of the Maximum Mean Discrepancy (MMD). The noise-adaptive MMD is trained on data distributions corrupted by increasing levels of noise, obtained via a forward diffusion process, as commonly used in denoising diffusion probabilistic models. The result is a generalization of MMD Gradient Flow, which we call Diffusion-MMD-Gradient Flow or DMMD. The divergence training procedure is related to discriminator training in Generative Adversarial Networks (GAN), but does not require adversarial training. We obtain competitive empirical performance in unconditional image generation on CIFAR10, MNIST, CELEB-A (64 x64) and LSUN Church (64 x 64). Furthermore, we demonstrate the validity of the approach when MMD is replaced by a lower bound on the KL divergence.

cs.LG↗
arXiv2024

Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models

We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach improves the overall predictive performance, especially when considering distributional shift between training and evaluation data, we here emphasize the perspective that online adaptation turns parameters into temporally changing states and provides a form of context-length extension with memory in weights, more in line with the concept of memory in neuroscience. We pay particular attention to the speed of adaptation (in terms of sample efficiency),sensitivity to the overall distributional drift, and the computational overhead for performing gradient computations and parameter updates. Our empirical study provides insights on when online adaptation is particularly interesting. We highlight that with online adaptation the conceptual distinction between in-context learning and fine tuning blurs: both are methods to condition the model on previously observed tokens.

cs.CL↗
arXiv2023

Kalman Filter for Online Classification of Non-Stationary Data

In Online Continual Learning (OCL) a learning system receives a stream of data and sequentially performs prediction and training steps. Important challenges in OCL are concerned with automatic adaptation to the particular non-stationary structure of the data, and with quantification of predictive uncertainty. Motivated by these challenges we introduce a probabilistic Bayesian online learning model by using a (possibly pretrained) neural representation and a state space model over the linear predictor weights. Non-stationarity over the linear predictor weights is modelled using a parameter drift transition density, parametrized by a coefficient that quantifies forgetting. Inference in the model is implemented with efficient Kalman filter recursions which track the posterior distribution over the linear weights, while online SGD updates over the transition dynamics coefficient allows to adapt to the non-stationarity seen in data. While the framework is developed assuming a linear Gaussian model, we also extend it to deal with classification problems and for fine-tuning the deep learning representation. In a set of experiments in multi-class classification using data sets such as CIFAR-100 and CLOC we demonstrate the predictive ability of the model and its flexibility to capture non-stationarity.

cs.LG↗
arXiv2023

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks. An even more ambitious goal is to build models that never stop adapting, and that become increasingly more efficient through time by suitably transferring the accrued knowledge. Beyond the study of the actual learning algorithm and model architecture, there are several hurdles towards our quest to build such models, such as the choice of learning protocol, metric of success and data needed to validate research hypotheses. In this work, we introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks, sorted chronologically and extracted from papers sampled uniformly from computer vision proceedings spanning the last three decades. The resulting stream reflects what the research community thought was meaningful at any point in time, and it serves as an ideal test bed to assess how well models can adapt to new tasks, and do so better and more efficiently as time goes by. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. The diversity is also reflected in the wide range of dataset sizes, spanning over four orders of magnitude. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks, yet with a low entry barrier as it is limited to a single modality and well understood supervised learning problems. Moreover, we provide a reference implementation including strong baselines and an evaluation protocol to compare methods in terms of their trade-off between accuracy and compute.

cs.LG↗
arXiv2023

Towards Compute-Optimal Transfer Learning

The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downstream tasks. However, the high computational and memory requirements to finetune or use these models can be a hindrance to their widespread use. In this study, we present a solution to this issue by proposing a simple yet effective way to trade computational efficiency for asymptotic performance which we define as the performance a learning algorithm achieves as compute tends to infinity. Specifically, we argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. We evaluate our method on the Nevis'22 continual learning benchmark that offers a diverse set of transfer scenarios. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.

cs.LG↗