Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow inference. To address it, we propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. Unlike previously developed DBM distillation techniques, the proposed method can distill both conditional and unconditional types of DBMs, distill models in a one-step generator, and use only the corrupted images for training. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks, and show that our distillation technique allows us to accelerate the inference of DBMs from 4x to 100x and even provide better generation quality than used teacher model depending on particular setup.

Learning conditional distributions $\pi^*(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^*$. However, acquiring paired data samples is often challenging, especially in problems such as domain translation. This necessitates the development of $\textit{semi-supervised}$ models that utilize both limited paired data and additional unpaired i.i.d. samples $x \sim \pi^*_x$ and $y \sim \pi^*_y$ from the marginal distributions. The usage of such combined data is complex and often relies on heuristic approaches. To tackle this issue, we propose a new learning paradigm that integrates both paired and unpaired data $\textbf{seamlessly}$ through the data likelihood maximization techniques. We demonstrate that our approach also connects intriguingly with inverse entropic optimal transport (OT). This finding allows us to apply recent advances in computational OT to establish a $\textbf{light}$ learning algorithm to get $\pi^*(\cdot|x)$. Furthermore, we demonstrate through empirical tests that our method effectively learns conditional distributions using paired and unpaired data simultaneously.

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search ~\cite{DBLP:conf/nips/SimhadriWADBBCH21}, this competition addressed filtered search, out-of-distribution data, sparse and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency over industry-standard baselines, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers. In this work, we investigate methods for cost-efficient inference and fine-tuning of LLMs, comparing local and distributed strategies. We observe that a large enough model (50B+) can run efficiently even on geodistributed devices in a consumer-grade network. This could allow running LLM efficiently by pooling together idle compute resources of multiple research groups and volunteers. We address two open problems: (1) how to perform inference and fine-tuning reliably if any device can disconnect abruptly and (2) how to partition LLMs between devices with uneven hardware, joining and leaving at will. In order to do that, we develop special fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput. We showcase these algorithms in Petals - a decentralized system that runs Llama 2 (70B) and BLOOM (176B) over the Internet up to 10x faster than offloading for interactive generation. We evaluate the performance of our system in simulated conditions and a real-world setup spanning two continents.

Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. % Popular text-conditional diffusion models offer various high-quality image manipulation methods for a broad range of text prompts. Existing diffusion-based methods already achieve high-quality image manipulations for a broad range of text prompts. However, in practice, these methods require high computation costs even with a high-end GPU. This greatly limits potential real-world applications of diffusion-based image editing, especially when running on user devices. In this paper, we address efficiency of the recent text-driven editing methods based on unconditional diffusion models and develop a novel algorithm that learns image manipulations 4.5-10 times faster and applies them 8 times faster. We carefully evaluate the visual quality and expressiveness of our approach on multiple datasets using human annotators. Our experiments demonstrate that our algorithm achieves the quality of much more expensive methods. Finally, we show that our approach can adapt the pretrained model to the user-specified image and text description on the fly just for 4 seconds. In this setting, we notice that more compact unconditional diffusion models can be considered as a rational alternative to the popular text-conditional counterparts.

Many NLP tasks benefit from using large language models (LLMs) that often have more than 100 billion parameters. With the release of BLOOM-176B and OPT-175B, everyone can download pretrained models of this scale. Still, using these models requires high-end hardware unavailable to many researchers. In some cases, LLMs can be used more affordably via RAM offloading or hosted APIs. However, these techniques have innate limitations: offloading is too slow for interactive inference, while APIs are not flexible enough for research that requires access to weights, attention or logits. In this work, we propose Petals - a system for inference and fine-tuning of large models collaboratively by joining the resources of multiple parties. We demonstrate that this strategy outperforms offloading for very large models, running inference of BLOOM-176B on consumer GPUs with $\approx$ 1 step per second, which is enough for many interactive LLM applications. Unlike most inference APIs, Petals also natively exposes hidden states of served models, allowing to train and share custom model extensions based on efficient fine-tuning methods.

The current approaches for efficient NNS mostly belong to three separate lines of research. The first family of methods, Recently similarity graphs became the leading based on partition trees (Bentley, 1975; Sproull, 1991; paradigm for efficient nearest neighbor search, McCartin-Lim et al., 2012; Dasgupta & Freund, 2008; Dasgupta outperforming traditional tree-based and LSHbased & Sinha, 2013), hierarchically split the search space methods. Similarity graphs perform the into a large number of regions, corresponding to tree leaves, search via greedy routing: a query traverses the and query visits only a limited number of promising regions graph and in each vertex moves to the adjacent when searching. The second, locality-sensitive hashing vertex that is the closest to this query. In practice, methods (Indyk & Motwani, 1998; Datar et al., 2004; Andoni similarity graphs are often susceptible to local & Indyk, 2008; Andoni et al., 2015) map the database minima, when queries do not reach its nearest points into a number of buckets using several hash functions neighbors, getting stuck in suboptimal vertices. In such that the probability of collision is much higher this paper we propose to learn the routing function for nearby points than for points that are further apart. At that overcomes local minima via incorporating information the search stage, a query is also hashed, and distances to about the graph global structure. In particular, all the points from the corresponding buckets are evaluated.